That is the metal waste paradox. You pay for good material, then treat it like junk because your process cannot see it.

A hard clean-up of the bone yard can recover instant value. You can turn dead stock into scrap cash and free up floor space. That first sweep can cover a big chunk of your first year of GoSmarter. Then you lock in gains by logging offcuts at source before buying fresh material.

This is not theory. It is a process and purchasing fix.

Why the bone yard quietly drains profit

Most yards drift into chaos for the same reasons:

• offcuts get labelled by hand, then labels fade
• location data lives in someone’s memory
• planning systems trust old records, not real stock
• buyers stop trusting inventory data and reorder “just in case”

If your planner cannot find a remnant in 10 seconds, it does not exist for production.

That drives three losses at once:

• Cash loss from avoidable new-stock purchases
• Space loss from racks and yard zones blocked by unknown material
• Speed loss when teams spend time searching instead of cutting

Selling to scrap has a place, but only after you have proven reuse is not possible. The UK waste hierarchy puts reuse ahead of recycling for a reason (UK Government).

The 48-hour clean-up that can fund the rollout

Start with one focused exercise. Do not overcomplicate it.

Step 1: Sweep, sort, tag

For 48 hours, run a dedicated yard sweep.

• assign a temporary ID to every unknown bar, plate, and bundle
• capture grade, dimensions, estimated weight, condition, and location
• split material into three lanes: reusable, rework, scrap

This gives you immediate visibility.

Step 2: Release value fast

Move true scrap through your normal recycler route for immediate cash recovery. Move reusable stock back into planning queues before your next purchase cycle.

Track four numbers during the clean-up:

• tonnes identified
• tonnes reusable
• tonnes scrapped
• space released (racks or square metres)

You are converting ghost inventory into decisions.

Step 3: Prove the business case with your numbers

Now run the maths with your own data using the Business Case Calculator.

Model the combined impact of:

• reduced new-stock purchasing
• reduced waste leakage
• reduced handling/admin time
• better space utilisation

This turns a “software pitch” into a decision backed by operational evidence.

Why legacy systems keep the mess alive

Most legacy Enterprise Resource Planning (ERP) systems were not built for real-time shop-floor remnant control. They assume stock records are clean and updated instantly. They are not.

At the saw, teams cut material. Offcuts appear. If no one logs that event in the moment, system data drifts from physical reality.

Then your nesting and planning tools inherit bad stock data. Buyers lose trust. They order new bars and sheets because uncertainty feels safer than stock risk.

That behaviour protects delivery dates in the short term. It damages margin every week.

The workflow that stops bone-yard relapse

A one-off clean-up helps once. A shop-floor-first workflow keeps the gains.

With GoSmarter, operators can log offcuts at the point of cut. The remnant becomes a searchable digital asset immediately, with dimensions, grade, and location.

A practical day-to-day flow looks like this:

1. Operator cuts a parent length and records the remnant in-app.
2. Remnant inherits traceability details and current location.
3. Planning checks reusable stock first during cut-list generation.
4. Purchasing reviews reusable coverage before raising new orders.
5. Teams consume, reserve, or scrap remnants with a clear reason code.

No grease-pencil mystery pieces. No “we think we had one in Bay 3” guesswork.

Reuse first, scrap second

Steel’s recyclability is a major industry advantage, and global steel production uses substantial scrap input every year (World Steel Association).

But from a margin perspective, “recyclable” is not the same as “optimal”.

If a remnant can fulfil a live order, reuse usually beats scrap disposal financially. Scrap should be the deliberate final step, not the default outcome of poor visibility.

This is where process discipline and software work together:

• clean process turns yard chaos into usable categories
• live data stops categories drifting back into chaos
• purchasing controls lock in the financial upside

How this pays for itself

The payback comes from compounding gains, not one magic metric.

1) Process gains

• less time spent searching and checking stock
• fewer planning delays from uncertain availability
• cleaner yard flow and faster picking

2) Purchasing gains

• fewer panic buys
• fewer duplicate buys of material already on site
• better timing of replenishment

3) Waste gains

• more remnants consumed internally
• less usable stock downgraded to scrap
• more intentional scrap sales from clearly unusable stock

When teams ask, “Will this software pay back?”, this is the answer: it pays back by fixing the decisions you make every day.

If you want to quantify it before rollout, use the Business Case Calculator with your clean-up baseline.

Frequently Asked Questions

Go deeper

• Scrap, Waste & Yield Optimisation — practical guidance on reducing waste and protecting margin
• Spreadsheet-to-System Planning — replace disconnected planning files with live operational data
• Cutting Optimiser — generate remnant-aware cut plans from real stock positions
• Midland Steel Case Study — measurable operational impact from AI-led workflows

If your yard is full of unknown metal, that is not “normal”. It is trapped margin.

Do the clean-up. Run the numbers. Then stop the pile from coming back with a workflow that pays for itself.

A medium-sized metals service centre handling 200 deliveries a month (even at a conservative 5 minutes per cert to open, read, type, save, and link to the right record) burns through 16 hours of staff time on cert admin alone. Every month. Before anything goes wrong. Then add the time spent hunting for a missing cert before an audit, arguing with a supplier over a mis-entered heat number, or chasing a customer approval because the grade on the cert does not match the order.

AI tools for compliance-driven document operations fix the foundation of the problem: they read the document, extract the data, validate it, and file it where it belongs. No human in the loop for every single certificate. GoSmarter’s MillCert Reader is built specifically for this in metals, handling the format chaos of real-world mill certs that would defeat a generic OCR tool.

Here is what this guide covers:

• What compliance-driven document operations actually mean at a metals manufacturer
• Why the manual process fails at two specific and predictable points
• What AI tools actually do mechanically — not marketing copy, the mechanics
• How GoSmarter’s MillCert Reader handles it without replacing your existing stack
• What changes operationally when you automate

Here’s how to fix it.

What Compliance-Driven Document Operations Mean in Metals

In a metals business, “compliance-driven document operations” is not a consultant’s phrase. It describes a specific, daily reality: every piece of material you buy, process, or sell must be traceable to a document that proves it is what you say it is.

The core document is the Material Test Certificate (MTC) — also called a mill cert or mill test report. An MTC records the heat number, chemical composition, and mechanical test results for a specific batch of material. Under EN 10204, the European standard for inspection documents for metallic products, you will deal with either a 3.1 certificate (validated by the manufacturer’s authorised quality representative) or a 3.2 certificate (validated by an accredited independent inspector). Which type you need depends on your customer’s specification or the structural application the material goes into.

Beyond MTCs, compliance document operations in metals typically cover:

• Delivery documentation — delivery notes that must reconcile with the cert, the purchase order, and your incoming goods inspection
• Production Part Approval Process packs — required by automotive customers before you can supply into their production line
• Inspection records — dimensional and visual inspection results linked to specific batches
• Non-conformance reports — documenting material that falls outside specification and the corrective actions taken
• Customer-specific declarations — chemical composition forms, conflict minerals declarations, REACH compliance statements

All of this needs to live somewhere retrievable, survive your next Quality Management System (QMS) audit, and be producible on demand when a customer disputes a delivery or a regulator asks an inconvenient question. If you are ISO 9001-certified, document control is not optional. It is audited.

Your Enterprise Resource Planning (ERP) system probably has a document attachment function. Most manufacturers use it inconsistently. That is the polite version.

Why Manual Cert Management Keeps Failing

The Audit Fire Drill

Every quality manager in metals knows the feeling: audit date confirmed, panic starts. Three people spend the afternoon before the auditor arrives reconstructing a paper trail that should have been automatic. Heat numbers get cross-referenced by hand. Someone finds a cert for the wrong grade. Someone else finds a cert with no matching heat number at all.

This is not a people problem. It is a process problem. When certs arrive as PDFs in an email, get saved by whoever opens them first, in whatever folder name made sense to them that day, the system was always going to fail. You cannot build reliable traceability on a foundation of inconsistent individual behaviour.

The Data Entry Gap

The second failure point is the gap between what the cert says and what your ERP says. A cert arrives. Someone reads it, types the key values — heat number, grade, yield strength, elongation percentage — into the ERP or a spreadsheet. Errors creep in. Certs for similar grades look almost identical. When the data is wrong, the error does not surface until a customer dispute or a failed incoming inspection.

A service centre processing 200 deliveries a month handles over 1,000 individual certificate field values in manual data entry each month. Independent research on manual data entry tasks puts typical error rates at 1–4%. At 1,000 fields, that is 10 to 40 wrong values in your system every single month, silently waiting to cause a problem.

What AI Tools Actually Do

AI tools for compliance-driven document operations are not magic. They apply a specific combination of techniques to a specific problem.

Optical character recognition (OCR) reads the text from a PDF or scanned cert image. Basic OCR tools have existed for decades. The problem in metals is that cert formats vary enormously. A cert from SSAB looks nothing like one from a Chinese cold-roller, a Turkish rebar mill, or a domestic bright bar producer. Standard OCR chokes on rotated text, scanned tables, unusual fonts, and anything that deviates from a clean digital PDF.

Machine learning-based extraction goes further. Instead of just reading the characters, it understands what they mean. It identifies the heat number even when it appears in a different position, in a different format, or under a differently labelled column header. It reads the mechanical properties table even when the column order changes between suppliers. It handles the variability that defeats standard OCR.

Validation and matching closes the loop. The AI does not just extract the data. It checks it. Does the grade on the cert match what was ordered? Does the heat number already exist in the system against a different grade? Are the mechanical properties within the required specification range? Anything that fails a check gets flagged for human review, not silently filed with an incorrect value.

This is what GoSmarter’s MillCert Reader does. It ingests the cert, extracts the structured data, validates it against your order and specification, and pushes the result into your workflow. No one transcribes a number wrong at 4:30 on a Friday afternoon.

How GoSmarter’s MillCert Reader Handles It

Reading Certs Without the Formatting Fight

MillCert Reader handles the format variability that defeats standard OCR tools. It is trained on real mill cert layouts from hundreds of suppliers, including European mills, North American producers, and Asian cold-rollers, covering scanned documents and PDFs with inconsistent layouts, faint ink, and varying table structures.

You upload the cert directly, or connect an email inbox so certs are processed automatically on arrival. The tool reads the document. Chemical composition, mechanical test results, heat number, product form, grade designation: all extracted and structured in seconds. What used to be a 5-minute per-cert task becomes a background process.

Linking Certs to the Right Material

Extraction on its own is not enough. The data needs to be in the right place. MillCert Reader links each cert to the corresponding purchase order line, so when you look up a batch of material, the cert is already attached. It is not buried in a folder somewhere.

If you are running an existing ERP or document management system, GoSmarter connects to it. You do not have to rebuild your stack to get this working. For teams building tighter compliance practices, this is where the real time saving lands: no more “where is the cert for that heat?” It is attached to the material record, automatically, every time.

The Difference Between Filing Certs and Owning Your Compliance

There is a meaningful gap between “we have the certs somewhere” and “we can produce the cert for any batch within 30 seconds.” The first gets you through most audits most of the time. The second is what your highest-value customers in aerospace, automotive, and structural fabrication are increasingly requiring as a condition of supply.

Metals manufacturers who have automated their compliance document workflows consistently report the same shift: quality managers spend less time preparing evidence for audits and more time preventing non-conformances. That is the real return. Not just faster filing, but a QMS that functions under pressure rather than breaking at the exact moment it matters most.

For a broader look at cutting document burden across your whole operation, see 7 Ways to Reduce Paperwork in Metal Manufacturing.

Start Here: What to Do This Week

You do not need to replace your ERP. You do not need a six-month IT project. The fastest path to audit-ready cert management starts with one step: get your incoming mill certs out of shared inboxes and into an automated extraction pipeline.

Run GoSmarter’s MillCert Reader on your next batch of incoming certs. See what comes back structured and linked against what currently gets typed by hand or filed in a folder nobody can reliably find. The difference is visible on day one.

Frequently Asked Questions

At the end of 2025, Italy had 26 EAFs in operation, with combined crude steel capacity of 23.9 million tonnes per year. Three significant new investments are set to raise those figures further. Together, they will add well over 2 terawatt hours (TWh) of additional annual power demand to Italy’s industrial grid. They will reshape the country’s position in European steelmaking for the next generation.

The operational picture for any team running or planning an EAF in Italy today is clear: more capacity, higher energy pressure, and no margin for sloppy data management.

Why Italy Became Europe’s EAF Capital

Economics drove Italy’s move to electric steelmaking long before decarbonisation became a European policy priority. Post-war Italy had limited domestic iron ore reserves but a ready supply of scrap metal from industrial reconstruction. EAFs, which melt recycled scrap rather than smelting ore, made financial sense from the start.

The result was a dense cluster of scrap-based mini-mills, concentrated in the north and centre of the country, focused on long products: rebar, sections, and wire rod for the construction and engineering sectors. Alfa Acciai, based in Brescia, is one of the largest examples, producing up to 2.5 million tonnes per year. It is the kind of operation that grew up in Italy’s EAF tradition and has spent decades refining it.

By the time the rest of Europe began its painful reckoning with blast furnace decarbonisation, Italy had largely already made the switch. That structural head start explains the 90% figure. It also explains why Italy is now the test bed for the next generation of EAF investment.

Three Investments That Will Reshape the Map

Acciaierie Venete: New Furnace in Padova, Summer 2026

Acciaierie Venete is installing a new 100-tonne EAF at its Padova site, supplied by Danieli. The target output is 750,000 tonnes per year of green engineering steels. The furnace is expected to be operational in summer 2026.

When it comes online, the new unit will add approximately 0.5 TWh of additional power demand per year. That is a significant draw from a single furnace and underlines the scale of energy commitment each new EAF installation represents for the grid.

This is not just a capacity addition. New EAFs of this generation are designed with data integration as a standard feature, not an afterthought. The operational complexity of managing scrap inputs, tracking heat numbers, and producing compliant mill certificates does not simplify at higher volumes. It compounds.

Metinvest and Danieli at Piombino: A €2.5bn Green Steel Overhaul

The largest project currently underway is a joint venture between Metinvest and Danieli at Piombino, Tuscany. The total investment is €2.5 billion. The plan involves two Direct Reduced Iron (DRI) EAFs, targeting 2.7 million tonnes per year of hot-rolled steel.

The DRI-EAF route has two stages. First, the process reduces iron ore to DRI using natural gas or, in principle, green hydrogen. Then an Electric Arc Furnace melts it. It produces substantially lower carbon emissions than blast furnace steelmaking and underpins Europe’s most ambitious green steel projects.

Piombino has a long steelmaking history. Its workforce knows heavy industry. This is not just a furnace upgrade; it is a fundamental change in production chemistry. The first EAF is targeted for around 2029. At full operation, the project will add an estimated 1.8 TWh to Italy’s annual industrial electricity consumption. As with all projects of this scale, the timeline carries political and operational uncertainty.

Acciaierie d’Italia: Taranto’s Complicated Transition

Italy’s only remaining large-scale blast furnace operation sits at Taranto, run by Acciaierie d’Italia. Italy’s government has authorised the site for up to 6 million tonnes per year and mandated a transition to EAF-based production.

Taranto is the outlier in this picture. It spent years entangled in legal, environmental, and political complications. The rest of the Italian steel sector moved forward while Taranto sat in limbo. The transition timeline remains subject to ongoing uncertainty. When Taranto completes the shift to EAF steelmaking, it will be the single largest blast furnace conversion in Italian history. Italy’s already dominant EAF share will push even higher.

Italy’s Energy Problem Is Not Going Away

Italy’s steel sector consumed an estimated 13.8 TWh of electricity in 2025. That figure represents 42% of the country’s total industrial electricity demand. No other sector comes close.

Italian electricity prices are structurally high. The grid depends heavily on imported gas. Global gas market volatility flows directly into the cost of every heat. EAF steelmaking is electricity-intensive by design. Electric arcs melt scrap above 1,600°C. That draws enormous power over a short melting cycle. When power prices spike, margins compress immediately and without warning.

The new capacity coming online at Padova and Piombino will push that electricity demand higher still. For existing operators, the pressure to extract maximum yield from every heat is not new. What is new is the scale. Investors and customers alike now expect new facilities to manage it properly from day one.

High electricity prices do not just make EAF steelmaking more expensive. Every tonne of avoidable scrap costs twice what it should. Same for every missed cut and every manual process that slows throughput.

What Running an EAF Actually Demands

The public conversation about EAFs focuses on their carbon credentials. The day-to-day operational reality is considerably less tidy.

An EAF charges a blend of scrap metal grades. The quality and chemical composition of that scrap varies by batch, by supplier, and often by day. Getting the chemistry of a heat right requires careful scrap management. That means tracking which grades are in the yard, what the residual element content is, and how to blend efficiently to hit the target specification.

Every heat produces a mill certificate (also called a Mill Test Certificate (MTC)). That document records the heat number, chemical analysis, and mechanical properties of the steel produced. Downstream fabricators, service centres, and construction contractors need it before they can use the steel. A rebar supplier who cannot produce the MTC for a given heat number cannot deliver to any properly run site.

At the volumes Italian EAF mills operate, this process generates thousands of certificates per year. Managing them manually is a recognised operational burden across the sector. That means filing PDFs, re-entering heat numbers into Enterprise Resource Planning (ERP) systems, and searching for missing documents before a customer audit.

Cutting plans add a further layer of complexity. EAF mills produce billets or coils that are cut to customer order. Every cut that generates excessive offcut is lost yield. When electricity costs spike and scrap prices are volatile, there is no fat in the margin for avoidable material waste.

The combination of energy pressure, variable scrap inputs, and rigorous traceability requirements makes EAF operations one of the most data-intensive environments in metals manufacturing. The mills that manage that data well protect their margins. The ones that rely on manual processes absorb every market shock in full.

New Facilities, New Expectations

The investments at Padova and Piombino are not being built to replicate the workflows of older mills. They are being designed as digital-first facilities, with data integration and process automation built in from the architecture stage. That shift creates both an opportunity and a benchmark.

For the engineers and production managers who will run these sites, the expectation from day one is clear. Operational tools must be connected. Traceability must be automated. Yield data must be live, not reconstructed at the end of the month from paper records.

That same expectation is also spreading to existing Italian EAF operators. Customers, auditors, and investors are all asking for better data. The mills that can provide it will win business. The ones that cannot will be managing the deficit for years.

Where GoSmarter Fits the EAF Operator’s Toolkit

GoSmarter built its suite specifically for metals manufacturers dealing with this complexity: variable scrap inputs, high-volume certificate management, cutting optimisation, and real-time inventory visibility.

GoSmarter’s Mill Certificate Automation reads EAF mill certificates automatically, extracting heat numbers, chemical compositions, and mechanical test results from PDF documents without manual re-entry. For a mill producing hundreds of heats per week, that is not a convenience. It is an operational necessity.

Scrap, Waste & Yield Optimisation tracks material in, yield out, and waste generated at every stage of production. EAF operators juggle variable scrap grades and tight electricity costs. Accurate real-time yield data changes what decisions are possible on the shop floor.

GoSmarter’s Cutting Optimiser applies algorithmic cutting plans to minimise offcut waste across a batch of customer orders. Fewer remnants mean more shipped tonnes from the same volume of melted steel. For a mill supplying engineering steels to tight dimensional specifications, every cut counts.

Inventory Management gives operators a live picture of stock by grade, heat number, and length: the data structure that mirrors how steel businesses actually work, rather than how a generic warehouse system assumes they do.

New greenfield EAF investments are the natural fit. But older Italian EAF operators running manual processes on ageing systems have the same underlying requirements. A greenfield site builds good habits from day one. An established mill retrofits them later. Both are achievable. One is considerably cheaper.

Go Deeper

• Mill Certificate Automation — how GoSmarter reads EAF mill certs automatically
• Scrap, Waste & Yield Optimisation — cut the waste coming off your EAF charge
• Cutting Plans (Cutting Optimiser) — optimise every cut to protect yield
• Inventory Management — track your scrap and finished stock in one place

Frequently Asked Questions

Source: Argus Media — New Furnaces to Support Italian Steel Power Demand

The project is called Driving Sustainability in Manufacturing (DSM). It was funded through the Welsh Government’s VInnovate (Interregional Innovation) programme. It brought together Nightingale HQ, CTAG, and technology partner OVEUN: two organisations from Galicia, one from Wales.

The Pressure Manufacturers Are Under

The market is squeezing steel and metals manufacturers from every direction:

• Energy costs that compress margins quarter after quarter
• Skills shortages that stretch already lean teams
• Sustainability targets that require hard evidence, not promises
• Critical processes still running on paper, spreadsheets, and manual judgement

GoSmarter.ai was built for exactly this situation: the metals AI toolkit that cuts waste and automates compliance without replacing your Enterprise Resource Planning (ERP), ripping out your spreadsheets, or running a twelve-month implementation project. The platform works on top of the systems you already use, including email-based order intake, CSV stock exports, and ERP platforms like Dynamics, Epicor, or Sage. It surfaces real operational insights from the factory data you are already generating. Ruth Kearney and Steph Locke founded Nightingale HQ in 2018 to fix a specific problem. Nobody else was tackling the long-standing inefficiencies across the metals sector directly.

What CTAG Brings to the Table

CTAG is a national research centre in Spain. Its Manufacturing and Digital Transformation Division covers Smart Factories, Cybersecurity, and Quantum Computing. Its simulation facilities and specialist teams know automotive production from the inside out.

Combining CTAG’s simulation capability with Nightingale HQ’s data and AI expertise created something neither could have built alone. Galicia’s strong automotive manufacturing base, paired with Wales’s established strengths in digitalisation and technology, made this an unusually well-matched collaboration.

“VInnovate showed the real value of international collaboration. By combining CTAG’s advanced simulation facilities with Nightingale HQ’s data and AI capabilities, we were able to develop and test solutions that support more sustainable and efficient manufacturing processes.”

Dr. Angel Dacal, Head of Innovation and Impact in Manufacturing, CTAG

How the Digital Twin Works

Work centred on building a Digital Twin that simulates a real automotive manufacturing process. The system creates a near real-time representation of production, covering:

• Simulation of energy consumption and emissions
• Monitoring of production outputs
• Evaluation and optimisation of operational strategies

The Nightingale HQ team analysed energy data extracted from robotic systems. They built a visualisation layer that surfaces insights from multiple analytical modules. That makes complex machine data readable and actionable for production teams.

What the Data Actually Shows

The solution ingests raw machine-activity data, cleans it automatically, and converts it into interactive analytics. Production teams get clear visibility into:

• Machine activities: robotic operations, sanding, polishing
• Energy usage patterns over time
• Statistically detected anomalies: GoSmarter flags unusual spikes or drops before they become costly problems

Analysis started with a single machine dataset and expanded to multi-machine coverage. Cross-machine decision support is in development.

Explore the Digital Twin platform: ctagdt.gosmarter.ai

Watch the Project Overview

The video Driving Sustainability in Manufacturing — CTAG and Nightingale HQ project overview walks through the 12-month DSM project: how the Digital Twin was built, what the energy data reveals about robotic manufacturing processes, and the commercial outcomes for GoSmarter.ai.

What the Project Delivered for Nightingale HQ

The VInnovate project did more than prove a technical concept. It accelerated Nightingale HQ’s product development in ways a standard Research and Development (R&D) budget rarely allows.

Ruth Kearney, CEO at Nightingale HQ, said:

“The support gave us the time and resources to undertake the research needed to validate the technology in real factory environments and bring our first commercial product to market. It enabled us to test new ideas working on Digital Twin systems developed by our collaborators, where we get to learn from other experts and transfer valuable knowledge.”

The project enabled Nightingale HQ to:

• Launch its first commercial GoSmarter.ai product and gain early market traction
• Validate real-world use cases within metals and automotive manufacturing
• Scope further innovations tailored to steel and metals manufacturers
• Build lasting research partnerships with specialist institutions like CTAG, with deep expertise in automotive and industrial manufacturing

Steph Locke, Head of Product at Nightingale HQ, said:

“Wales’s success rests on its manufacturing base and, increasingly, on its growing tech startup community. The VInnovate programme enabled us to collaborate internationally and achieve more for manufacturing through technology. Beyond funding, the Welsh Government’s innovation advisors bring real, practical value to R&D-intensive businesses.”

Already Delivering on the Factory Floor

The Research and Development (R&D) work done during DSM feeds directly into the impact GoSmarter.ai is having on real factory floors today. GoSmarter.ai targets four outcomes that operations directors and finance directors both care about:

Mill Cert Processor — cert PDF to linked stock record in seconds

When a certificate PDF arrives, GoSmarter reads it, extracts the heat number, grade, spec, and quantity, and links that data to your live stock count automatically. Any cert that does not match the order spec is flagged immediately, before the material moves. That means non-conformances caught early, a full audit trail built automatically, and up to one month of manual processing time reclaimed per production manager per year. Once certs are digitised and linked, that data feeds straight into cutting plans and job scheduling.

• Scrap reduction: Long product optimisation trials show 20–50% reductions in production scrap, depending on product mix. Service centres processing bar and structural steel see the highest gains.
• On-Time In Full (OTIF) improvement: faster cert processing means material is confirmed to job spec before it is too late to source an alternative. Fewer last-minute substitutions means fewer missed delivery dates.
• Decarbonisation: less scrap means less steel produced for the same output. Less scrap means lower emissions. That is a direct, measurable contribution to decarbonisation targets.

Nightingale HQ’s founders were recently on site in Port Talbot, delivering AI readiness training to the leadership team at Tata Steel UK. Tata Steel is investing in low-carbon steelmaking. GoSmarter is helping make that transition stick. Both strands of work align directly with the Welsh Government’s Innovation Strategy, particularly its economy and climate missions.

What Comes Next

VInnovate proved the concept. Now Nightingale HQ is using the Welsh Government’s SMART Flexible Innovation Support (SFIS) programme to fund the next phase of GoSmarter.ai product development. The focus: deeper automation, sharper waste tracking, and tools that help manufacturers meet sustainability targets with real operational data rather than estimates.

FAQs

Further Reading

The resources below provide deeper context on the DSM project, the Digital Twin platform, and GoSmarter.ai’s wider work with metals manufacturers.

• GoSmarter.ai platform
• GoSmarter pricing and data handling
• Driving Sustainability in Manufacturing — project video
• Driving Sustainability in Manufacturing — Digital Twin platform
• CTAG — Automotive Technology Centre of Galicia
• Business Wales: Nightingale HQ success story
• Building AI-Readiness at the Heart of UK Steel Manufacturing
• Nightingale HQ Partners with King’s College London

The evening opened with an education session from Gareth I. Jones on what drives entrepreneurial growth and how elements of the Massachusetts Institute of Technology (MIT) Industrial Liaison Programme could be replicated here in Wales to better support founders and strengthen the ecosystem. Then the pitches began.

GoSmarter walked away with more than a good room. The conversations that continued well after the formal sessions confirmed what the team already knew: the problem GoSmarter is solving is real, persistent, and well overdue for a fix.

The Problem: Metals Manufacturing Is Drowning in Paper

Walk into most metals factories in the UK and Ireland today and you will find two things that should not go together: precision machinery running to tight tolerances, and admin processes that would not look out of place in a corner shop from thirty years ago.

Mill certificates printed, stamped, and filed in binders. Production schedules on whiteboards. Cutting plans calculated in spreadsheets that break every time someone with institutional knowledge retires. And somewhere in that factory, every single day, someone is re-keying data that already exists on a supplier PDF, because no one has built the bridge to get it into the system automatically.

This is what the GoSmarter team calls the Silver Tsunami. The metals sector is facing an ageing workforce retiring faster than the industry can replace them. Skilled operators who held production knowledge in their heads are leaving. Their replacements need systems that capture that knowledge and put it to work. Instead, factories are spending hours per week on manual cert data entry, chasing heat numbers before audits, and calculating offcut reuse by hand. Every hour spent on that is an hour not spent making metal.

What GoSmarter Does

GoSmarter.ai automates the paper-heavy, time-consuming processes that keep metals manufacturers stuck, without ripping out the core systems they already have. Three products sit at the heart of it.

Mill Certificate AI reads supplier mill certificates automatically, extracts the relevant data, and pushes it into the workflow. No re-keying. No lost PDFs. No panicked cert hunt the morning of an audit. The system handles scanned documents, clean digitals, and phone photos alike, and processes each page in under 15 seconds.

Cutting Optimiser calculates the most efficient way to cut stock against open orders, minimising scrap and tracking offcuts for reuse across future jobs. Where manual approaches typically leave between 3% and 8% of material on the floor, GoSmarter targets the industry benchmark of 2.5% or better.

Inventory and Traceability gives the shop floor real-time visibility of what is on hand, where it is, and what it has been tested against, so quality teams can answer traceability questions in seconds rather than hours.

Rajesh Nair, Chief Executive Officer (CEO) of Tata Steel UK, noted that GoSmarter helped “create clarity, shared understanding, and momentum around how AI can support their people, operations, and long-term strategy.” Tony Woods, CEO at a partner metals business, was more direct: “The integration of AI and digital tracking has significantly improved our operational efficiency and sustainability performance.”

These are not pilot projects. GoSmarter has recurring revenue, active customers across the UK and Ireland, research and development collaborations with enterprise metals manufacturers including Tata Steel UK, and a patent filed on its core intellectual property.

The Round: £500k EIS, 45% Already In

GoSmarter is raising £500,000 under the Enterprise Investment Scheme (EIS) at a £1.5 million valuation. As of the Women Angels of Wales pitch on 24 March, 45% of the round is already secured: £200,000 in non-dilutive grant funding alongside £25,000 in cash investment.

The raise covers an 18-month runway to the key milestones that set up the next stage of growth. The cap table has three rows. The intellectual property is patent-filed. The investor target is a 10x return on investment within four years, with an exit via trade sale or management buyout targeted around 2031.

The market numbers make a clear case. GoSmarter’s total addressable market (TAM) sits at approximately 2% of the global metals market, valued at £3.2 trillion and growing at 4.1% per year. In the UK and EU alone, there are around 400,000 metals small and medium-sized businesses (SMBs) in the target profile: land-and-expand Software as a Service (SaaS) customers who need exactly what GoSmarter delivers, and who tend to start with one product and grow from there.

GoSmarter is looking for investors who are active in AI, SaaS, or manufacturing, who care about sustainability and backing diverse founders, and who want a seat at the table as board members or advisors rather than passive names on a cap table.

Why Women Angels of Wales

Events like this matter because they are where the Welsh tech ecosystem builds its real connections.

Women Angels of Wales is not a passive investment club. The group backs founders with conviction and genuine sector expertise. The education session from Gareth I. Jones set a tone that matched the ambition in the room: rigorous, forward-looking, and genuinely interested in how Wales builds a stronger platform for high-growth founders.

The Development Bank of Wales and the British Business Bank both support the network, which reflects the broader commitment to growing Welsh startups past seed rounds and into the markets they deserve. Three founders, one evening, one room of serious investors. That is how ecosystems get built, and GoSmarter is proud to be part of that story.

The next Women Angels of Wales Education and Pitch event takes place on 1st July. If you want to find out more about angel investing or attending future events, get in touch at hello@womenangelsofwales.com.

Want to Back the Round?

The EIS raise is open now. If you invest in AI, SaaS, or manufacturing, care about sustainability, and want to back a team with real traction and a defensible product, get in touch with Ruth directly: ruth@gosmarter.ai

GoSmarter is looking for engaged investors who want to help shape a product already changing how metals manufacturers work, not just a line on a portfolio page.

Less paper. More metal. Let’s build it together.

Nightingale HQ co-founders Steph and Ruth are heading to the Mid Wales Manufacturing Group (MWMG) in April. They’re joining forces with the Welsh Government High Value Manufacturing (HVM) Cluster to run a hands-on session on Continuous Improvement through the Latest Technology and they’re ready to tell it straight.

What the session covers

The short version: how to get your factory working smarter without making your life harder.

The longer version: over two hours, we’ll cover how modern technology (including artificial intelligence, or AI) can help manufacturers do more with less. That means saving time, cutting material waste, and lowering your carbon impact. Not because it sounds good in a press release, but because it actually works.

We’re not here to sell you a vision board. We’re here to show you what’s possible today, with tools that real manufacturers are already using.

Meet the people running the session

Steph and Ruth are the co-founders of Nightingale HQ. Their software is built specifically for metals manufacturers. Their mission is simple: help more Welsh businesses succeed by making better use of modern technology.

They’ve spent years watching manufacturers fight the same battles: spreadsheets that don’t talk to each other, paperwork that eats the day, admin that a computer should be doing. GoSmarter exists to sort that out.

Manufacturers using GoSmarter have cut document processing time from hours to minutes, improved material traceability across the supply chain, and freed their teams from the tedium of manual data entry. This session is their chance to show you what that looks like in practice.

What you’ll actually leave with

Our goal is straightforward. By the end of the session, participants will be:

• Informed about what modern technology can do for a manufacturer like you
• Confident that it’s not as complicated or risky as it sounds
• Equipped with practical ideas and a clear sense of where to start

We’ll explore how people and processes can benefit from smarter technology. That could mean your team spending less time on repetitive tasks. It could mean catching quality issues before they become scrap. It might mean finally understanding where your energy and material costs are going.

AI doesn’t have to mean robots taking over the shop floor. It can mean your best people spending their time on work that actually matters.

What is Continuous Improvement, and why does it matter right now?

Continuous Improvement (CI) is the practice of making small, steady changes to your operation rather than waiting for a big overhaul. In metals manufacturing, that might mean tightening up your stock management, reducing the time it takes to process incoming material certificates, or catching a quality issue one step earlier in the process.

The problem is that CI has traditionally relied on people spotting patterns manually. That takes time, and it depends on the right person being in the right place at the right moment.

Modern technology changes that. Sensors, software, and AI can watch your operation continuously. They flag the issues and your team fixes them.

Three signs your operation could benefit from this conversation:

• You’re catching quality problems after the job is done, not during
• Your team spends a significant chunk of each shift on paperwork or data entry
• You don’t have clear visibility on where your material losses are occurring

If any of those sound familiar, you’re in the right place.

How to try new technology without betting the business

One of the biggest blockers we hear from manufacturers isn’t “we don’t want to change.” It’s “we can’t afford to get it wrong.”

Most manufacturers assume AI means a six-figure project and six months of disruption. It doesn’t have to. We’ll show you what low-risk actually looks like.

The workshop will cover the funding and support available to Welsh businesses. That includes grants for skills development, pilot projects, and implementation support. There are real ways to try new technology without betting the business. Too many manufacturers don’t know they exist, and we’re happy to share what we know.

The MWMG is a brilliant community of manufacturers who are serious about improving. The Welsh Government HVM Cluster exists specifically to help them do it. We’re proud to be part of that conversation.

Come ready with questions

This isn’t a lecture. It’s a conversation. If you’re already thinking about where technology could help your operation (or where you’ve tried something and it didn’t stick), bring those questions.

Big thanks to the Mid Wales Manufacturing Group (MWMG).

We’ll see you there.

FAQs

Government Intervention to Secure the Industry

British Steel operates the last two remaining blast furnaces in the UK. The Scunthorpe plant employs 3,500 people directly and supports tens of thousands of jobs in the wider supply chain. However, the business has faced significant financial challenges, with operational losses and mounting costs. According to the National Audit Office, keeping the plant running cost £377m by January this year. That figure could exceed £1.5bn by 2028 if nothing changes.

Concerns escalated when Jingye announced plans to shut down the Scunthorpe site in March 2025. Jingye had acquired the company out of insolvency in 2020. Closing the site would have ended the UK’s capacity for primary steel production. Blast furnaces create steel from iron ore from scratch. Electric arc furnaces recycle scrap metal instead.

To prevent this, ministers designated the steel industry as vital to national security. That opens the door to nationalisation on security grounds. A government spokesperson commented, “We have been clear that safeguarding UK steelmaking is our priority. We continue to engage with the owner to find a solution that protects workers, production and the national interest, and we will not comment further while discussions are ongoing.”

Ownership Negotiations and Industry Challenges

Efforts to negotiate a deal with Jingye have been ongoing. Earlier this month, the government reportedly offered £100m for British Steel. Jingye rejected it, holding out for over £1bn. If further talks fail, ministers may impose a deadline to finalise the transfer of economic control within weeks.

The government’s intervention is also driven by the need to stabilise the company before seeking potential private buyers. British Steel has already attracted interest, with Miami-based investor Michael Flacks declaring himself “very” interested in February. Officials have indicated that there are other parties showing early interest as well.

However, any new owner would need to commit to significant investment to modernise the Scunthorpe plant. This would include replacing its polluting blast furnaces with electric arc furnaces (EAFs), which are less reliant on fossil fuels.

Industry Response and National Security Implications

The director general of UK Steel, Gareth Stace, expressed support for the government’s plans, saying, “This would provide vital certainty for the workforce, the company’s customers and the wider supply chain at a critical moment. Maintaining domestic production capability for British Steel’s products is essential not only for economic growth but also for our national security and resilience. This will hopefully mark the beginning of a clear and credible long-term plan for British Steel.”

To protect domestic producers, the government recently announced plans to double tariffs on imported steel. It will also reduce the volume that can be brought in from abroad. The aim is to stop cheap Chinese steel from driving down market prices.

Future Prospects for British Steel

While British Steel remains an important player in the UK economy, its path to stability has been fraught with challenges. Greybull Capital acquired the company in 2016, but it collapsed into insolvency three years later. Jingye then bought it out of administration. The Scunthorpe plant was reportedly losing £700,000 per day when Jingye announced closure plans last year. Recent efforts to increase output aimed to cut those losses.

The nationalisation of British Steel marks a significant moment for UK industrial strategy. The government moved quickly to preserve domestic steelmaking, protect jobs, and keep the sector viable long-term. But with costs rising and major investment still needed, the future of British Steel remains unresolved.

Timeline of Key Events

• 2020 — Jingye acquires British Steel out of insolvency, pledging investment in the Scunthorpe site.
• March 2025 — Jingye announces plans to shut down the Scunthorpe blast furnaces, triggering emergency government intervention.
• April 2025 — Ministers assume direct control of day-to-day operations to keep the plant running.
• January 2026 — The National Audit Office reports the government has spent £377m keeping British Steel operational.
• February 2026 — Miami-based investor Michael Flacks publicly declares interest in acquiring the business.
• Early 2026 — Government tables a £100m offer for the company; Jingye holds out for over £1bn.
• March 2026 — Steel designated as vital to national security. Full nationalisation expected within weeks.

What This Means for UK Fabricators and Service Centres

If you buy long products — sections, rail, wire rod, or structural beams — from British Steel, you have a direct interest in how this plays out.

Nationalisation itself does not mean production stops. In the short term, it may actually bring more certainty than the months of instability under Jingye. The Scunthorpe site is expected to keep running under government control while a longer-term buyer is found.

But there are real risks worth planning for now:

• Supply continuity: Transition periods create operational uncertainty. If British Steel is a primary source of structural sections or rail for your operation, review your buffer stock and qualify alternative sources before you need them.
• Pricing: The government’s doubled import tariffs make cheap overseas substitutes less attractive. Domestic prices could firm up. They could also swing unpredictably, depending on how quickly any new owner commits to production targets.
• Lead times: Ownership changes stretch lead times without warning. Build that contingency into your procurement schedule. Waiting for a problem to arrive on the shop floor is the expensive approach.

The steel may keep flowing for now. Procurement teams that track this closely will be far better placed than those that assume business as usual.

What to Watch Next

Three things worth monitoring over the coming weeks:

1. The nationalisation vote — legislation is expected in parliament imminently. The timeline and any conditions placed on the transfer of ownership will determine how quickly the situation stabilises.
2. Electric arc furnace investment — any new owner or government plan must commit to replacing the blast furnaces with EAFs, which use scrap steel rather than iron ore and produce far lower carbon emissions. The scale and timing of that investment determines whether Scunthorpe has a viable long-term future.
3. Import tariff impact — the doubled tariffs are designed to protect domestic producers. Watch whether they push up prices for fabricators sourcing domestically, and whether that changes your landed cost calculations for imported alternatives.

Frequently Asked Questions

Read the source

Manual Gemba walks and sticky notes had their moment. They’re slowing you down now. The old way of Kaizen is reactive: spotting problems only after they’ve cost you time and money. In metals manufacturing, where downtime eats margins for breakfast, that’s a luxury no one can afford.

Here’s the good news: AI-powered Kaizen takes the same improvement mindset and puts it on steroids. Forget waiting weeks to find inefficiencies - AI spots them in real time. Predictive maintenance slashes downtime by up to 70%, and tools like GoSmarter automate tedious tasks like scrap calculations and mill certificate processing. That’s more time for engineers to focus on what matters.

The Old Way vs. The Smart Way

The bottom line? Stop wasting time on paperwork and start solving real problems. Let’s dive into how AI is changing the game.

Build AI Systems To Optimise Any Process (with Kaizen)

1. Traditional Kaizen Methods

Traditional Kaizen is built on five core principles [3]:

• Customer focus — every improvement decision starts with the end user
• Waste elimination — cut anything that doesn’t add value
• Direct observation — go to the the actual place that value is created (Gemba), don’t guess from a spreadsheet
• Team empowerment — the people doing the work find the fixes
• Transparency — problems are visible, not hidden

At its core lies the PDCA cycle (Plan, Do, Check, Act) [1]. On the shop floor, managers perform Gemba walks to benefit from direct observations of workflows and to pinpoint areas for improvement [3]. The ultimate aim is to tackle the 3 Ms [1]:

• Muda — waste: defects, overproduction, waiting
• Mura — uneven workflows that create peaks and troughs
• Muri — overburdening people or kit until something breaks

Efficiency Gains

When done right, traditional Kaizen can yield impressive results. Take Lockheed Martin, for instance: over five years, they slashed manufacturing costs by more than 33% and halved delivery times [3]. Similarly, Toyota’s transformation in the late 1950s under Taiichi Ohno’s guidance is legendary where they reduced die-change times from 24 hours to just 3 minutes. This shift enabled small-batch production, which exposed quality issues almost immediately [4]. The philosophy driving these successes is simple: small, continuous improvements create momentum and show value to employees [3]. These achievements highlight the potential of Kaizen while also setting the stage for understanding its limitations in scaling and sustaining these methods.

Implementation Complexity

The real challenge with Kaizen lies not in its techniques but in the mindset shift it requires. It demands full commitment from everyone including executives, managers, and workers alike. Without this, resistance can emerge, sometimes even leading to staff turnover [3]. Smaller organisations often find it easier to secure this buy-in due to closer manager-employee relationships. In contrast, larger corporations with rigid systems can struggle [3]. Tools like Nemawashi which is a practice of informal discussions to build consensus before decisions are formalised are invaluable for fostering alignment, though they can be time-consuming [3]. This preparatory work is crucial for adapting traditional Kaizen to meet the dynamic needs of modern manufacturing.

Scalability

One major limitation is the heavy reliance on manual tools and isolated data systems, which makes it harder to quickly identify root causes [1]. The PDCA process, when done manually, can slow down responses in fast-moving environments [1]. Traditional Kaizen often takes a reactive approach - you only fix the oil leak after it’s already made a mess [1]. Another issue is the loss of “tribal knowledge” when experienced workers retire, especially if this expertise hasn’t been documented or digitised [1]. In today’s manufacturing world, these manual and reactive methods can turn into obstacles rather than solutions.

2. AI-Powered Kaizen (e.g., GoSmarter)

AI doesn’t replace Kaizen - it amplifies it. Instead of relying on occasional Gemba walks to uncover issues, machine learning keeps an eye on every parameter in real time[6]. The PDCA cycle, which traditionally moved at the pace of manual data gathering, now operates fast enough to identify and address problems within hours rather than weeks[11]. This evolution shifts management from being reactive to proactive, blending time-tested methods with cutting-edge data-driven strategies.

Efficiency Gains

AI-driven tools offer impressive boosts in efficiency. For instance, dynamic parameter adjustments can lead to an average 15% improvement in production efficiency[9]. Predictive maintenance not only increases uptime by 20% but also reduces maintenance expenses by 10%[11].

Waste Reduction

AI goes beyond improving efficiency and it tackles waste head-on. Take Muda, for example: optimised cutting plans and precise tracking of offcuts through GoSmarter can reduce scrap by as much as 50%[2]. Mura, or uneven workflows, is smoothed out when AI schedules production runs to eliminate bottlenecks. As for Muri, or overburdening, predictive analytics help balance workloads before they become overwhelming[6][11].

What makes this metals-specific is how the AI thinks about offcuts. A generic planning tool marks a short remnant as scrap. GoSmarter tracks it by grade, length, and heat number and offers it up for the next job that needs a short bar. That’s the difference between an AI that understands your yard and one that just runs a cut-length algorithm.

As Tarun Mathur, Global Digital Lead for Metals at ABB, puts it, “AI is making sustainability and decarbonisation more profitable by linking carbon reduction with operations excellence.”

Implementation Complexity

Integrating AI into manufacturing isn’t without its challenges, echoing some of the hurdles faced in traditional Kaizen. One significant technical obstacle is working with outdated ERP systems, many of which date back to the 1990s. AI integration often requires custom solutions to bridge these gaps[6]. GoSmarter plugs directly into existing infrastructure including sensors, PLCs, and spreadsheets without a rip-and-replace project or a six-month IT queue.

On the cultural side, gaining frontline workers’ trust in AI can be tricky. Mercedes-Benz’s MO360 platform tackled this by empowering employees to directly interact with AI for bottleneck solutions, staying true to Kaizen’s focus on team involvement[8].

As Jan Bosch explains, “kaizen AI generators” are systems that evolve continuously, requiring deep integration rather than functioning as simple add-ons[10].

Starting small with tools like scrap rate calculators that can help prove the benefits of AI before committing to a larger rollout[2].

Scalability

Platforms like GoSmarter’s Production Planner are designed to scale effortlessly, connecting shop-floor automation with enterprise systems without delay[7]. Tesla, for example, uses AI to fine-tune production efficiency and streamline supply chains across multiple locations[9][10]. Unlike traditional Kaizen, which can lose momentum when key personnel retire, AI preserves expert knowledge in machine learning models that continue to evolve and improve. This scalability captures the essence of continuous improvement in today’s digital landscape.

Advantages and Disadvantages

Traditional Kaizen and its AI-powered counterpart each have their own strengths and challenges. The traditional method is straightforward: it doesn’t require advanced tech like data pipelines or machine learning. Instead, it relies on team commitment and the willingness to hold workshops. But there’s a catch - it’s slow. Traditional PDCA (Plan-Do-Check-Act) cycles often run on a monthly or quarterly basis, relying on manual observation. On the other hand, AI-powered Kaizen operates at a completely different speed, running multiple cycles daily through real-time telemetry[5]. This means AI can pinpoint bottlenecks as they happen. However, the trade-off is the complexity of implementation. It does need solid data pipelines, MLOps know-how, and guardrails to stop automated changes going sideways.

Scalability is another area where these approaches differ significantly. Traditional Kaizen struggles to handle large, complex systems due to its manual nature. In contrast, AI-powered Kaizen embeds process knowledge into machine learning models that can evolve on their own. GoSmarter’s Production Planner links shop-floor automation to enterprise systems without middleware headaches, letting improvements roll out across every site.

As Hemant Panda explains, “Kaizen and PDCA do not disappear with AI; they become faster, more continuous, and more autonomous”[5].

The table below highlights the major differences between these two approaches, underlining the importance of combining their strengths.

The best approach lies in integrating these methods. Combining the steady, incremental improvement philosophy of traditional Kaizen with the speed and adaptability of AI creates a balanced strategy.

Manu Mulaveesala cautions, “In the rush to capitalize on AI’s potential, many organizations are focused on rapid, radical transformation rather than sustainable progress. The Kaizen philosophy offers a valuable counterbalance”[12].

The key is to start small. Prove the benefits on a smaller scale before expanding. And remember: AI isn’t a magic wand. Automating flawed processes only amplifies their inefficiencies. Focus on refining your workflows first, then let AI take them to the next level. Using free toolkits for smart manufacturing will show you exactly where the waste is hiding.

Kill the Spreadsheets. Keep the Philosophy.

AI doesn’t replace Kaizen. It supercharges it. The philosophy of continuous improvement hasn’t changed. The speed and scale of it have. What used to take weeks in traditional PDCA cycles now takes hours. Real-time telemetry replaces the manual walkabout and it never misses a shift. The goal isn’t to abandon the principles that built modern manufacturing. It’s to kill the spreadsheets slowing them down.

For metals manufacturers, the next steps are straightforward: start small, prove the results, and then scale up. Free tools like scrap rate or emissions calculators can help you pinpoint areas of high waste before making any major investments. Focus on specific pain points such as the 120+ hours a year spent manually processing MillCerts by deploying targeted AI solutions, rather than diving into a massive six-month ERP overhaul.

As Tony Woods, CEO of Midland Steel, explains: “Smart technology choices can have a direct, measurable impact on reducing carbon emissions in steel manufacturing. The integration of AI and digital tracking has significantly improved our operational efficiency and sustainability performance” [2].

The most effective strategies layer AI onto existing systems instead of tearing everything down. For instance, GoSmarter’s approach connects directly to legacy ERPs via APIs, digitises mill certificates using OCR, and optimises cutting plans to slash scrap by 50%. This lets you modernise outdated processes without waiting years for IT to complete a full system overhaul. It’s a practical way to blend Kaizen’s traditional principles with the speed and precision of digital tools.

The metals industry doesn’t need flashy buzzwords; it needs tools that eliminate muda (waste) without adding complexity. AI-powered Kaizen does just that: it removes tedious manual work, captures critical know-how before experienced planners retire, and transforms chaotic PDF stacks into actionable insights. By combining AI with Kaizen, manufacturers can stick to the philosophy of continuous improvement while achieving execution speeds that were previously unimaginable.

Refine your processes first, then let AI take them to the next level. Start small and focus on one production line, measure the results, and then expand. That’s how you’ll run faster, greener, and without any surprises.

FAQs

Here’s the fix: AI doesn’t wait for problems to show up - it predicts them. By analysing every data point in real time, AI flags issues 15–30 minutes before your process drifts out of control. No guesswork. No missed trends. Just smarter decisions, faster.

The Old Way vs. The Smart Way

Let’s face it: the old way is costing you money. AI-driven SPC cuts false alarms by 40%, slashes defect rates by 50%, and saves you up to £1 million annually on quality costs.

Now, let’s dig into how this works - and how to get started.

How AI Predicts Quality Problems in SPC

AI Techniques That Improve SPC

AI is transforming Statistical Process Control (SPC) by analysing multiple variables at once, something traditional methods like Shewhart charts struggle with. These older tools focus on one variable at a time, overlooking how factors like temperature, pressure, and material grade interact. AI, however, uses multivariate analysis techniques - such as Gradient Boosting Decision Trees and Random Forests - to uncover the “golden-run” parameter combinations that keep production on track [4].

Advanced methods like time series forecasting (using LSTM networks and ARIMA models) predict future data points, while anomaly detection with autoencoders flags subtle data shifts that standard SPC might miss. Additionally, pattern recognition with Convolutional Neural Networks interprets complex control chart patterns, such as cyclic trends or mixtures, automatically [6]. These innovations have tangible benefits: AI-driven SPC systems can reduce false alarms by over 40% and cut the mean time to detect issues by 30% to 85%, depending on the process [5][6]. Together, these tools enable manufacturers to use historical data to define operational norms and predict deviations before they lead to problems.

How Historical SPC Data Trains AI Models

AI learns what “good” production looks like by analysing historical data from successful runs. The quality of this data is critical, as Jason Chester from Advantive emphasises:

“Artificial Intelligence is only as good as the data it learns from” [4].

If your SPC data is messy - filled with mislabelled entries, missing timestamps, or inconsistent part numbers - the AI won’t filter out the noise; it will amplify it. By feeding the system 3–6 months of clean historical data, such as temperature logs, pressure readings, material properties, and tool wear metrics, the AI can establish a baseline of normal production behaviour [2]. It identifies variable combinations that consistently lead to zero defects, creating a predictive envelope to flag deviations before they escalate.

Companies that prioritised disciplined data collection before implementing AI saw a 45% reduction in the time spent cleaning up data [4]. Once the system is operational, it retrains itself automatically when enough new data is collected, adapting to changing conditions without requiring manual adjustments [7].

Real-Time Monitoring: Turning Data into Alerts

After training, AI moves into real-time monitoring, analysing incoming data from sensors, gauges, and IoT devices. Unlike traditional SPC, which relies on manual checks every 30 minutes, AI evaluates every data point continuously, applying SPC rules to both current and predicted data [7]. If the model forecasts that upcoming measurements will breach control limits, it sends alerts through APIs, email, SMS, or enterprise messaging systems - well before defects occur [7].

This dual-layer approach, combining multivariate statistical tools like Hotelling’s T² with machine learning classifiers, identifies subtle anomalies that single-variable charts might overlook [5][6]. For example, an automotive manufacturer using an AI-powered “SPC 4.0” system improved mean detection times by 85% and reduced manual inspection workloads by 60% [5].

As Jason Chester summarises:

“SPC and AI are not competing technologies. SPC secures the right data at the right moment; AI converts that data into actionable foresight” [4].

How to Implement AI in SPC

Step 1: Digitise and Organise Your SPC Data

For AI to work effectively, your data needs to be clean and standardised. Start by reviewing your current quality records - inspection logs, manual SPC charts, and spreadsheets - to spot gaps, errors, or formats that AI can’t easily process [2].

Next, upgrade your data collection methods. Install sensors like wireless monitors for temperature, pressure, and vibration to switch from manual sampling to continuous data capture [3]. Use industrial protocols such as MQTT, OPC-UA, or Modbus to connect equipment [1]. If you’re working with older machinery, edge gateways can bridge the gap between legacy PLCs and modern sensor systems [8].

Standardising your data is critical. Ensure each record includes essential details like part numbers, revisions, lot numbers, machine IDs, shift information, and precise timestamps [4]. AI models rely heavily on clean data, and fixing these issues at the source can save significant time - some manufacturers have cut manual data-cleaning efforts by 45% [4]. Additionally, you’ll need a robust historical dataset, ideally covering 6–12 months or more, to train your models effectively [2].

Once your data is in order, you can move on to building predictive models based on key process parameters.

Step 2: Build and Train Predictive Models

Clean, well-structured data enables AI models to define baseline production parameters, paving the way for proactive quality control. Feed your system a mix of process parameters (e.g., temperature, pressure, speed), material properties (like composition or moisture levels), and environmental factors (such as humidity or vibration) sourced from your historical records [2]. Experiment with algorithms such as ARIMA, LSTM, and Gradient Boosting, selecting the best-performing one for your needs. Regular retraining - whether weekly, monthly, or triggered by new data - helps the models adapt to evolving conditions [7][6].

For example, in an automotive assembly test, Gradient Boosting achieved an 88% accuracy rate for defect prediction (0.82 F1-score), while CNNs excelled in vision-based tasks with 94% accuracy [5]. Use these models to establish a “golden run” envelope, where the AI identifies parameter combinations that consistently yield defect-free production. Any deviation from these parameters can then be flagged before issues arise [4].

With your models trained, the next step is to deploy them for real-time monitoring.

Step 3: Use AI for Real-Time Monitoring

Once trained, deploy your AI models to continuously evaluate incoming data. These systems analyse every data point in real time, eliminating the need for manual checks. They also apply SPC rules to both current and predicted measurements [7]. If the model predicts that upcoming readings will breach control limits, it sends alerts through APIs, emails, SMS, or enterprise messaging systems - often 2–15 minutes before defects occur [3].

For high-speed production lines, edge hardware can be used to achieve sub-5ms inference times, avoiding delays caused by cloud processing [3]. To enhance accuracy, combine traditional SPC tools, such as Hotelling’s T² charts, with machine learning classifiers. This dual-layer approach reduces false alarms by over 40% and cuts detection times by 30% to 85% [5][6].

Start small by piloting the system on a single high-value or high-scrap production line. Validate the AI’s predictions against actual results before rolling it out across the entire plant [4]. Integrate AI alerts into existing SPC dashboards to ensure a smooth transition - forcing operators to learn a new interface can slow adoption. As Jason Chester from Advantive notes:

“SPC and AI are not competing technologies. SPC secures the right data at the right moment; AI converts that data into actionable foresight” [4].

For metals manufacturers, implementing AI-driven SPC means digitising existing workflows and connecting legacy equipment to modern monitoring systems — turning manual processes into real-time quality insights.

Insights Hub Quality Prediction - Introduction

Old Way vs. New Way: The Impact of AI on SPC

Traditional Statistical Process Control (SPC) has always been a reactive process. Manufacturers rely on manual sampling to spot defects, often discovering issues only after significant damage has been done. AI-driven SPC flips this script entirely. Instead of waiting for defects to appear, it predicts quality issues 15–30 minutes before they happen. By analysing hundreds of process parameters simultaneously and inspecting every unit - not just a sample - AI identifies problems early, preventing them from spiralling into costly mistakes [2][3].

AI systems don’t just predict problems; they’re also smarter about reducing false alarms. Unlike static thresholds used in traditional SPC, AI adapts to changing process conditions, cutting false alarms by 40% [3]. The result? Manufacturers see a 30% faster Mean Time to Detection (MTTD) for process shifts and yield improvements of up to 1.7% in precision manufacturing [9][3]. For a £50 million manufacturer, reducing the Cost of Quality (COQ) from 4% to 2% could save an impressive £1 million annually [2]. And that’s not all - internal failure costs (like scrap and rework) drop by 60–70%, while external failure costs (returns and warranties) fall by 70–80% [2].

The speed of root cause analysis is another game-changer. Traditional methods can take 1–4 weeks to narrow down potential causes; AI does it in just 2–3 hours, evaluating hundreds of variables at once [2]. AI-based vision systems also boost defect detection rates by up to 90%, while increasing throughput by over 25% by allowing operators to focus on real issues instead of chasing false alarms [3][4].

Comparison Table: Traditional SPC vs. AI-Driven SPC

Here’s a side-by-side look at how AI-driven SPC outperforms traditional methods:

These numbers make one thing clear: AI isn’t just a tool - it’s a game-changer for SPC in metals manufacturing. But this isn’t about replacing human expertise. It’s about giving quality engineers the tools they need to spot and solve problems before they escalate.

Conclusion

Why AI is the Future of SPC

Traditional SPC methods react to problems after they’ve happened, often documenting defects too late to prevent costly consequences. AI flips this approach on its head, turning SPC into a predictive tool that stops quality issues before they snowball. By analysing hundreds of variables - like temperature, vibration levels, or material lot changes - AI can predict potential quality problems and reduce defect rates by 40–60%. This kind of efficiency slashes overall quality costs by 30–50% [2][3]. For a £50 million manufacturer, that could mean cutting annual quality failure costs from £2 million to £1 million.

Tasks that once took weeks, like root cause analysis, now take hours [2]. False alarms drop by 40% because AI models adjust dynamically to actual operating conditions, unlike traditional static thresholds [3]. And with 100% inline inspection replacing manual sampling, you’re no longer guessing whether one inspected part reflects the entire batch [3]. As Will Jackes from iFactory puts it:

“The shift from reactive to predictive quality isn’t optional - it’s essential” [3].

This marks a major leap forward, moving from outdated reactive quality control to a proactive, data-driven approach.

Take Action: Stop Manual Work

If your SPC process still leans on spreadsheets, manual sampling, and intuition, you’re not just wasting time - you’re losing money. The benefits of AI-driven SPC are clear, and the time to modernise is now.

Start by evaluating your current SPC methods. Clean up your historical data and pilot AI on a production line with high scrap rates [4]. Collaboration is key - pair your data scientists with quality engineers. While AI can point to anomalies, it’s the domain experts who can identify the physical causes [4]. Once your data is in order, AI can transform it into actionable insights, helping you streamline processes and boost production efficiency.

FAQs

The 8 KPIs every metals manufacturer should track: Overall Equipment Effectiveness (OEE), throughput rate, scrap rate, first pass yield, On-Time-In-Full (OTIF) delivery, energy per tonne, embodied carbon per tonne, and cost per tonne. Track these in real time and you can see exactly where you’re losing money — before the shift ends.

The Old Way vs. The Smart Way

Let’s break down the KPIs that matter most - OEE, scrap rates, energy efficiency, and cost per tonne - and how to build a dashboard that doesn’t just inform but transforms your operations.

Watch: OEE and KPIs Explained in Three Minutes

OEE, throughput, and yield are the three numbers that expose hidden losses most metals manufacturers never catch in time. This three-minute explainer shows why they matter and how to read them correctly.

Which Production Efficiency Metrics Should You Track?

Tracking production efficiency is the fastest way to find losses caused by downtime, slow cycles, or quality issues. These key performance indicators (KPIs) distinguish factories hitting their tonnage goals from those falling behind. They also set the stage for deeper insights into quality and waste management.

Overall Equipment Effectiveness (OEE)

OEE is the most critical number on your dashboard - it combines availability, performance, and quality into one percentage that reflects your actual capacity utilisation [4][5]. While 85% is considered world-class, most metals manufacturers operate between 60% and 75% [4]. For a steel plant producing 2 million tonnes a year, every OEE point represents about £10 million in revenue [6].

Display OEE in real time and you catch a problem in the first five minutes — not at the end-of-shift debrief. A loss waterfall visualisation can show exactly where capacity is being lost [7]. Often, the bottleneck lies in critical equipment like the continuous caster or hot strip mill - addressing these constraints can unlock higher throughput [6][5].

Throughput Rate

Throughput measures how many metric tonnes are produced per hour or shift, excluding scrap and rework. It’s a direct indicator of how well you’re using your equipment. For instance, if a rolling mill rated for 200 tonnes per hour only produces 140, you’re losing 60 tonnes of potential output every hour.

If throughput drops more than 8% below capacity for over 15 minutes, stop and find the cause [8]. That’s not a drift — that’s a problem. Real-time tracking helps uncover small stoppages and speed reductions that manual methods often miss. Automated tools typically detect 30% to 50% more performance losses than manual tracking [6][7]. Following throughput, assessing yield rate can give you a clearer picture of first-pass quality.

Yield Rate

Yield rate measures the percentage of metal meeting quality standards on the first pass, without requiring rework or repairs [4][1]. For example, if you produce 1,000 tonnes but only 850 are saleable, your yield rate is 85%, with 15% lost to waste. In multi-step processes like rolling and finishing, these losses can compound. For instance, a five-step process with a 95% yield at each step results in an overall yield of just 77.4% [4].

Pair yield rate with scrap and defect data and you’ll see exactly where quality breaks down and which process is to blame.

On-Time-In-Full (OTIF) Delivery

On-Time-In-Full (OTIF) measures the percentage of orders delivered complete and on the promised date. For service centres and fabricators, it is often the number that determines whether you keep a customer. Most metals businesses track it retrospectively — a spreadsheet updated after a delivery fails. By then, it is too late.

Real-time OTIF tracking means knowing today which jobs are at risk before they miss their date. That requires live visibility of what material is in stock, what is already committed to other orders, and whether the cutting schedule can deliver on time. When that data lives in disconnected spreadsheets, OTIF surprises are inevitable.

GoSmarter’s scheduling module shows live commitment status across all open jobs — which are on track, which are at risk, and which jobs are competing for the same material. Planners can act before a delivery slips rather than explain why it did.

Which Quality and Waste KPIs Matter Most?

Reducing waste and maintaining high-quality standards are constant challenges for any operation. Even when scrap metal prices are favourable, they rarely offset the combined costs of wasted materials and labour [9]. To gauge whether your operation is efficient or leaking profits, focus on these three KPIs. They complement production metrics by ensuring quality and minimising waste across shifts.

Scrap Rate

Scrap rate indicates the percentage of material that ends up unusable and cannot be salvaged. Ideally, most established operations aim to keep this below 5%, while top-tier plants often achieve rates under 2% [9][10]. A high scrap rate often points to issues with materials, equipment, or processes - such as misaligned fixtures, worn tools, or human errors in estimation [9].

Pareto charts can help you pinpoint which processes or machines are the main culprits for scrap [9]. For a deeper dive into benchmarks and reduction strategies, see the Scrap, Waste & Yield Optimisation hub.

For example, Midland Steel moved from manual cut planning to GoSmarter’s AI-driven Cutting Plans for rebar and structural sections. Scrap rate halved — recovering material per month that had previously been written off as offcut waste. Admin time dropped by over 120 hours a year: time that had been spent manually transcribing heat numbers and grades from PDF mill certificates into spreadsheets. With accurate, live stock data feeding their order commitments, the team also stopped over-ordering buffer stock to cover for planning uncertainty, cutting the working capital tied up in slow-moving bar. The whole change was live within a week [2].

Stop wasting raw material because someone guessed instead of measured [2].

Defect Rate

Defect rate measures the percentage of units with flaws, including those that can be repaired through rework. This metric is invaluable for identifying root causes, whether they stem from material inconsistencies, equipment malfunctions, or process deviations [14]. Real-time sensor data can detect issues like equipment drift or tool wear before they result in defects [9].

To reduce defects, investigate causes by machine, shift, or material batch. Standardising work instructions can help minimise variability, while preventive maintenance can address issues like misaligned fixtures or worn-out tools before they escalate [9].

First Pass Yield (FPY)

First Pass Yield goes a step further by measuring the percentage of products that pass quality checks on the first try without needing rework. An FPY above 95% is considered excellent, while anything over 90% is generally acceptable [11]. Achieving high FPY eliminates the “hidden factory” of rework, which drains extra labour, materials, energy, and accelerates equipment wear [11][12].

Consider a steel service centre processing structural sections and flat plate. By fitting IoT sensors at entry and exit points on each production line, the team identifies exactly which cut or forming step is generating the most rejects. Statistical process control (SPC) charts highlight tool wear trends before parts go out of spec [13]. Incorporating FPY data into your dashboards allows for immediate adjustments, bringing quality control in line with live production. For a five-step line with 95% yield at each stage, the overall FPY is just 77.4% [4] — tracking each step separately shows you exactly where to focus first.

Which Cost and Sustainability Metrics Should You Track?

Efficiency and quality only tell half the story. Cost and sustainability KPIs protect your margins and keep you on the right side of UK CBAM and ESG requirements. These metrics track production costs, energy consumption, and compliance — key elements increasingly required for ESG reporting.

Energy Efficiency (kWh per Tonne)

Energy efficiency measures how many kilowatt-hours are used to produce one tonne of metal. This metric impacts both your production costs and carbon footprint[3]. To calculate it, divide the total energy consumed by the tonnes of metal produced. If energy use increases, it could point to outdated equipment or poor production scheduling. Dashboards that break down energy consumption by shift or production line can help you identify and address inefficiencies[3][18]. Tracking embodied carbon alongside energy use ensures you stay on target for regulatory compliance and sustainability goals.

Embodied Carbon per Tonne

Embodied carbon measures the CO₂ emissions generated per tonne of metal produced. Fail a CBAM audit and you face import duties based on estimated — not actual — carbon content. Estimated carbon is always worse than measured. Companies relying on manual cert processing are one audit away from finding that out the hard way. Tracking embodied carbon per tonne is how you build the evidence trail before the auditor arrives[13][16]. Calculating embodied carbon manually from mill certificates can be slow and prone to errors.

For a full guide on automating certificate handling, see the Mill Certificate Automation hub.

GoSmarter’s MillCert Reader does more than extract numbers. When a PDF cert arrives — scanned, emailed, or downloaded from a supplier portal — GoSmarter reads the heat number, grade, spec, and mechanical properties, then checks them against your purchase order automatically. If something does not match, it flags the non-conformance before the material reaches the floor.

The cert stays linked to the stock record, the cut job, and the delivery note. When CBAM or a customer audit asks for material provenance, you are not scrambling through a filing cabinet.

Companies using AI-driven cutting plans have seen scrap rates drop by 20–50%, boosting margins while reducing embodied carbon per tonne of finished products[2][15]. Alongside emissions metrics, monitoring production costs per tonne is vital for maintaining profitability.

Cost per Tonne

Cost per tonne is a simple but powerful metric: divide the total production costs - including materials, energy, labour, and overhead - by the tonnes produced[17]. This figure is critical for protecting margins. Dashboards can break down these costs by shift or production line, helping you spot inefficiencies. For example, if one shift consistently incurs higher costs, investigate whether setup inefficiencies, excessive scrap, or energy waste are to blame. Companies focusing on these financial KPIs have achieved profitability increases of up to 20%[17]. Tying cost per tonne to First Pass Yield is also effective - products that meet quality standards on the first attempt use less energy and materials than those requiring rework[18][3].

How Do You Build a KPI Dashboard for Metals Manufacturing?

Creating an effective dashboard isn’t about cramming in every metric you can think of - it’s about giving your team access to the right numbers at the right time. The sweet spot? Around 8–10 key KPIs that align with your plant’s goals, whether it’s cutting downtime or slashing scrap rates [1]. Operators need live machine status and cycle times. Managers need OEE and cost-per-tonne trends. Build for both. These steps will help you customise a dashboard that works for everyone on your team.

Choose the Right KPIs

Your dashboard should reflect the needs of different roles within your operation. For example:

• Operations managers: Focus on OEE, capacity utilisation, and scrap rate.
• Maintenance teams: Track downtime, MTBF (Mean Time Between Failures), MTTR (Mean Time to Repair), and maintenance costs per unit.
• Quality teams: Monitor metrics like First Pass Yield (aiming for 98% in top-performing plants), defect rates, and customer returns [19].
• Leadership: Look at revenue per employee and manufacturing costs as a percentage of revenue to evaluate workforce efficiency and financial performance.

The key here is actionability. A KPI is only useful if it drives decisions - otherwise, it’s just noise [20]. Once you’ve nailed down the metrics that matter, ensure they’re powered by real-time data.

Connect Real-Time Data Sources

GoSmarter adds intelligence to the systems you already use — not replace them. You can be live in a day from a CSV upload. Connecting to an ERP, MES, or IoT sensors via API is available when you are ready, but never a requirement for day one [5]. GoSmarter runs in the browser, hosted in the EU, and your data belongs to you.

For real-time stock visibility, Metals Manager links your stock records, mill certs, and open orders — showing exactly what material is available, committed, and due for delivery. To see how AI cut-planning fits in, visit the Cutting Optimisation hub.

GoSmarter’s MillCert Reader uses AI to pull data straight from mill certificates — scanned or digital — without any manual typing [2]. Set up threshold alerts via SMS or email when critical metrics like downtime or scrap rates exceed acceptable limits [5]. Tackle issues as they arise, not after the fact.

Design Clear Visualisations

Once your data is flowing in real time, the next challenge is presenting it in a way that’s easy to understand. Use visual tools that make performance gaps obvious at a glance:

• Gauges: Ideal for real-time metrics like OEE.
• Line charts: Great for tracking trends over time.
• Pareto charts: Pinpoint the main causes of defects or downtime [1].

Add colour-coding (red, yellow, green) to flag urgent issues like production delays or quality problems. Always include a “Target vs. Actual” comparison to help teams see immediately whether they’re hitting their goals [1]. Make sure the dashboard is mobile-friendly so shop floor operators can access it on the go [21].

For plant managers, the dashboard should allow for a quick “5-minute check” of both financial and production performance. Reliability engineers, on the other hand, need tools for deeper analysis of failure modes and asset health [22]. The design should reflect these varied needs, ensuring everyone gets the insights they require to act effectively.

Getting Your Team on Board

A dashboard only works if people use it. The biggest reason KPI projects stall is not the technology — it’s the conversation that never happened. Before you build, agree on which three metrics the MD will look at each morning and what action each one triggers.

Start with the operators. Show them how the dashboard makes their shift easier — fewer audit panics, faster cert retrieval, less back-and-forth on material availability. If operators trust the data, they will flag when something looks wrong. That feedback loop is what makes dashboards improve over time.

Roll out in phases. Begin with one data stream — usually mill certificate processing, because it has an immediate, visible payback. A metals business processing 30 PDFs a week typically spends 8–15 minutes per document on manual entry. That is 4 to 7.5 hours every week, or up to 390 hours a year. At £30/hour for an administrator, that is up to £11,700 annually before any error correction. GoSmarter’s MillCert Reader handles the same task in under 30 seconds. Add scheduling and OTIF tracking in week two or three. You do not need a systems integrator or a project manager to get started.

Getting Started: The 30-Day Path

Not sure where to start? Most GoSmarter customers begin with one data stream — usually mill certificates, because that is where the most manual effort lives. Once certs are being read automatically and flowing into your stock record, the KPIs that depend on material data (scrap rate, yield, cost per tonne) start updating without anyone typing. That typically takes a day to set up. Scheduling and live commitment tracking come next, usually in the second or third week. You do not need a systems integrator, a data warehouse, or a project manager. You need a CSV export of your current stock and an hour on a call.

Stop Guessing. Build the Dashboard.

Pick 5–10 KPIs that match your plant’s goals: OEE, scrap rate, energy efficiency per tonne. That’s it. Everything else is noise[1]. Take ArcelorMittal as a case in point: by prioritising OEE, production yield, and cost per tonne, they achieved a 10% boost in OEE, a 15% increase in yield, and a 12% cut in production costs per tonne[17]. That’s the power of a dashboard that drives action, not just information.

Manual data tracking is a drain on resources. Tools like GoSmarter’s MillCert Reader eliminate this inefficiency, saving hundreds of hours annually by automatically extracting heat numbers and grades from mill certificates[2]. Similarly, AI-driven Cutting Plans typically reduce scrap rates by 20–50% — the largest gains come on long products like rebar and structural sections, where optimising cut sequences across mixed bar lengths can recover tonnes of material that would otherwise become offcut waste[2]. Your team can stop chasing data and start fixing the actual problem.

Modern dashboards go beyond recording metrics - they actively enhance performance. Real-time monitoring of metrics such as throughput, defect rates, and embodied carbon per tonne allows you to address potential issues before they snowball into costly problems. Companies optimising their financial KPIs have reported up to a 20% rise in profitability, while those prioritising operational efficiency have cut production costs by as much as 15%[17]. Raw metal alloy can make up over 50% of direct unit costs[23]. Even a 1% reduction in scrap goes straight to margin.

The metals sector is moving swiftly towards predictive maintenance, embedded analytics, and AI tools that turn raw machine data into decisions [5]. If you’re still relying on manual data entry and end-of-day reports, you’re not just outdated — you’re losing money. A dashboard that shows your team exactly what to fix — and when — is faster than any end-of-day report ever could be. Your competitors are already running these. Your spreadsheets are not a fair fight.

FAQs

Manually typing data from mill certs, hunting through filing cabinets, and fixing spreadsheet errors isn’t just tedious — it’s draining your profits. One UK steel stockholder spent over 120 hours a year just typing certificate data. That’s before you add stock counts, stockout delays, and error corrections. Together, manual tracking costs small manufacturers an estimated £14,100 every year [4].

The solution? Automated material tracking. AI tools now handle certificate data in seconds, link materials to their full history, and provide real-time stock updates. No more guessing, no more wasted hours, and no more compliance nightmares.

The Old Way vs. The Smart Way

Ready to stop losing time and money on outdated methods? Modern tools like GoSmarter’s MillCert Reader can digitise your certificates and transform your tracking process in minutes. Let’s fix this mess.

Manual Tracking: Hours Wasted, Money Burned

How Manual Tracking Works in Practice

In metals factories, manual tracking often revolves around clipboards, logbooks, and spreadsheets. Inventory movements - SKU, quantity, date - are logged in physical books or on bin cards attached to storage bins as materials come and go [5]. When audits or financial reports are due, operations grind to a halt while staff manually count every SKU in storage to create a “snapshot” [5]. It’s a time-consuming and disruptive process, offering only occasional glimpses into stock levels.

Managing mill certificates adds another layer of complexity. Staff must extract details like heat numbers, material grades, and chemical compositions from paper or PDF certificates and input them into ERP systems or shared drives [1]. At Midland Steel Manufacturing, for instance, employees had to manually match incoming deliveries with certificates and ensure the correct sections of multi-heat documents followed materials through cutting and dispatch [1]. This tedious process increases the risk of compliance errors. On average, small manufacturers spend 2–4 hours each week updating stock records [4], with some shop owners still relying on whiteboards or even memory to decide when to reorder parts [4].

As AirShop aptly put it:

The system ‘works’ in the sense that jobs get done and parts get ordered. But ‘works’ and ‘costs you money’ aren’t mutually exclusive. [4]

These inefficiencies not only slow operations but also lead to avoidable financial losses.

The True Cost of Manual Tracking

The financial impact of manual tracking is staggering. Small shops lose an estimated £14,100 annually just from manual tracking: £5,200 in labour for stock counts, £4,800 due to stockout delays, £2,600 correcting errors, and £1,500 in overstock carrying costs [4].

Errors are another major issue. Manual systems typically have error rates of 1% to 2% [5][7], which might seem minor but can snowball across thousands of transactions. Mistakes like transcription errors, illegible handwriting, and unit mix-ups only worsen the situation [7][8]. Because of this lack of trust in the data, many small shops carry 10% to 20% extra inventory as a safety buffer [4]. When a quality issue arises, tracing the problem back through manual records can take days, as inspection sheets, rework notes, and batch records are scattered across disconnected folders [3].

In short, manual tracking creates a data “black box” - you can see the final outcomes, but the process behind them is murky [3]. These hidden inefficiencies highlight the urgent need for a better, automated solution. Let’s examine how automation addresses these challenges next.

Watch: Automated Traceability in Minutes

What Automated Tracking Actually Fixes

The days of juggling clipboards and spreadsheets are over. Automated tracking systems now offer a faster, more precise way to manage materials, cutting costs and saving time.

How Automation Tackles Key Tracking Challenges

Gone are the hours spent manually entering heat numbers and chemical compositions from mill certificates. Tools like GoSmarter’s MillCert Reader use AI-driven OCR technology to extract this data in seconds. One production manager at Midland Steel Manufacturing, a rebar supplier operating across the UK, Ireland, and Norway, shared:

I logged in for the first time and was up and running in minutes. MillCert Reader now pulls all the key info - chemical composition, mechanical properties - automatically. This change cuts weeks of manual work to seconds. [1]

This efficiency adds up to roughly 10 hours saved every month on certificate-related tasks.

Unlike generic OCR systems, GoSmarter’s AI is built specifically for the metals industry. It understands complex terms like “Rp0.2”, separates data from multi-heat certificates, and even calculates Carbon Equivalence (CEQ) for CBAM reporting. All of this is done with precision, eliminating the painstaking manual effort these tasks would normally require [1]. The system also validates extracted data against expected ranges for specific grades and standards, flagging any discrepancies before they cause production issues [1].

At Midland Steel, this has led to real-time inventory visibility tied directly to mill certificates. Every piece of material now carries its full history - grade, heat number, mechanical properties - ensuring complete traceability [1][9]. When a cert arrives with a Carbon Equivalence outside the ordered range, or a heat number that doesn’t match the delivery note, GoSmarter flags it before the material reaches the shop floor. Non-conformances get caught at goods-in — not during a customer audit three months later.

Many metals businesses also use barcodes and RFID tags on individual bars, bundles, or pallets to replace handwritten bin cards, giving live visibility into stock levels and order commitments [9]. Most companies are up and running in a single day, with a clean fit into most ERP systems [1]. This creates an immutable audit trail and eliminates the need to sift through paper records. The result? Faster processes, fewer errors, and better oversight.

Tangible Benefits: Time, Accuracy, and Transparency

The shift to automation delivers clear, measurable improvements.

By automating mill certificate reading, users save over 120 hours annually — roughly three full workweeks [1]. That figure is based on a UK steel stockholder processing around 400 certs a month at 2–3 minutes of manual data entry per cert. A smaller site processing 100 certs a month typically saves 30–40 hours a year; a high-volume operation can save 200 or more. Accuracy gets a major boost too: while manual systems typically have error rates of 1% to 2%, automated systems achieve near-perfect accuracy by cross-checking data against industry standards [1]. Beyond the admin saving, the downstream effect matters equally. When stock records update from the cert in real time rather than from a spreadsheet refreshed once a day, planners make better commitments — fewer short-shipments, fewer last-minute material re-purchases, and measurably better on-time-in-full delivery.

Real-time updates reduce the need for excess safety stock, streamlining inventory and cutting waste [4]. If a quality issue arises, tracing the problem takes minutes instead of days, as every material is directly linked to its certificate and heat number [3].

This shift from periodic updates to continuous, real-time data transforms decision-making. Managers can instantly see what’s in stock, what’s allocated, and what needs reordering. This not only simplifies operations but also slashes administrative headaches.

GoSmarter offers a free trial, with plans starting at £275 per month [1]. Stop losing time and money on outdated methods. Invest in a system that works for you and your team.

Manual vs. Automated: Direct Comparison

Manual tracking leaves gaps in data and bleeds cash. Here is exactly how big the difference is.

The shift from manual to automated tracking is like moving from guesswork to certainty. Manual systems rely on humans to jot down data - often at the end of a shift or after delays - while automated systems capture events in real time, removing the need to rely on memory or delayed inputs [8].

The financial impact of sticking with manual methods can be staggering. For small manufacturers, hidden costs can run into thousands of pounds annually [4]. For mid-sized businesses, manual data entry alone can cost between £24,000 and £40,000 per year [12]. One striking example is a company spending £195,000 every year just to manually track production labour [2].

The efficiency gains with automation are undeniable. Take M&L Electrical, for instance - they slashed inventory management time by 99% after ditching manual methods. Smilebuilderz cut counting and replenishment time by 70%, and SMC, an electrical distributor, reduced procurement costs by 75% thanks to automation [6]. These aren’t just small wins - they’re transformative changes.

Performance Metrics: Manual vs. Automated

Let’s break this down further with a side-by-side comparison of key metrics:

Manual tracking is slow, error-prone, and costly. Automation is faster, more accurate, and pays for itself.

How to Transition from Manual to Automated Tracking

Switching to automation doesn’t have to upend your operations. Start by tackling your biggest headache - mill certificates. Many factories are buried under unorganised PDFs in shared drives, making them a nightmare to search or audit. Digitising these documents offers immediate relief while laying the groundwork for broader automation. This approach moves you from manual chaos to real-time data without tearing everything apart.

Start with High-Impact Tools, Then Expand

In December 2025, Midland Steel, a rebar manufacturer operating across the UK, Ireland, and Norway, adopted GoSmarter’s MillCert Reader. The result: 10 hours saved every month on certificate-related tasks.

Tools like GoSmarter’s MillCert Reader (starting at £275 per month) are built specifically for metals manufacturing. Unlike generic OCR, which often stumbles over industry-specific terms like “Rp0.2” or multi-heat certificates, this system handles them effortlessly. It processes certificate pages in just 5 to 15 seconds and automatically renames files by heat number, making them easy to find even during the transition [1][13].

Once you’ve digitised your certificates, it’s easy to scale up. You could move to full inventory tracking with tools like Metals Manager (starting at £400 per month), or use AI-powered cutting plans to slash scrap waste [14]. Cutting optimisation works by fitting jobs to the actual stock available — accounting for remnants, partial lengths, and material already committed — so fewer bars get scrapped as offcuts. Customers on long products typically recover 20–50% of the scrap they were generating, depending on their product mix.

Preparing for Long-Term Requirements

After addressing immediate challenges, it’s time to think about future needs, especially compliance and integration. Manual tracking simply can’t keep up with modern regulatory demands. For example, the EU’s Carbon Border Adjustment Mechanism (CBAM) already requires manufacturers to track Carbon Equivalence (CEQ) data - something that’s nearly impossible with manual systems [1]. Tools like GoSmarter automatically pull this data from certificates, ensuring you’re audit-ready without extra hassle.

The good news? You don’t need to replace your existing ERP or endure long integration timelines. GoSmarter sits alongside whatever you already run — Infor, Epicor, Microsoft Dynamics, Sage, or a bespoke system — reading in your data via CSV or REST API, and writing cert records, live stock updates, and cut plans back out the same way. Your ERP stays the system of record. GoSmarter adds the operational intelligence layer on top, without a rip-and-replace project [1][13]. To keep things running smoothly, set up clear naming conventions and assign responsibilities for uploading, verifying, and editing data. This approach ensures a clean, ISO 9001-compliant digital audit trail [13].

Stop Burning Cash on Manual Processes

Manual tracking drains over £14,100 a year from small manufacturers — and that’s just the measurable cost [4]. Automated systems achieve near-perfect inventory accuracy, reducing error rates from the 1–2% that manual methods routinely produce to near-zero [1]. They slash order processing times from two days to four hours. At £275 a month for MillCert Reader, if your team currently spends 10 hours a month on cert data entry at a fully-loaded cost of £35/hour, you’re spending £350 a month to do what GoSmarter does automatically. Month one, you’re already ahead. In today’s fast-moving industry, having accurate, real-time data isn’t just a nice-to-have; it’s a necessity for staying compliant and competitive.

This isn’t about jumping on the latest tech trend - it’s about survival. Your competitors are already ahead, digitising their processes to quote faster, meet compliance standards like CBAM with ease, and respond to market demands more effectively. Relying on spreadsheets and filing cabinets? That’s a recipe for slower operations and inflated costs.

Start with the biggest headache: mill certificates. Tools like GoSmarter’s MillCert Reader (starting at £275 per month) eliminate the time-sucking data entry that eats up hours every week [1]. Once your certificates are digitised, expanding to full inventory tracking or even AI-driven production scheduling becomes a natural next step.

The Longer You Wait, The More It Costs

The efficiency gains and cost savings from automation make it an obvious choice. Manual processes are not just outdated - they’re a drain on resources and a barrier to growth. Automated material tracking is no longer optional for metals manufacturers that want to run leaner, faster, and more sustainably. The real question isn’t whether you should automate - it’s how much longer you can afford to lose money on manual methods [4].

Try GoSmarter for free at gosmarter.ai and see how quickly you can turn paperwork chaos into actionable insights. Upgrade today to cut waste, boost efficiency, and stay ahead. Your team - and your profits - will thank you.

Frequently Asked Questions

The fix is real-time inventory management. It’s not just about knowing what’s in stock. It’s about knowing where it is, what it’s committed to, and how to use it smarter. Digital tools like RFID, barcode scanning, and AI-powered systems turn chaos into clarity.

Let’s break it down step by step.

Why Sticky Labels Don’t Survive a Metal Shop (And What Does)

Step 1: Move to Digital Inventory Tracking

Switching to digital inventory tracking is the first step to solving the headaches caused by manual processes. As mentioned earlier, relying on handwritten records or manually entering data into Excel often leads to costly mistakes. A simple typo in a heat code or a misread number can create phantom inventory that doesn’t exist or make actual stock seem to vanish. These errors pile up over time, leaving your records increasingly unreliable.

Digital tracking simplifies this by automating the process. Instead of manually entering part numbers or digging through filing cabinets for mill certificates, you just scan a barcode, and the system handles the rest. The impact is immediate - inventory discrepancies typically drop by over 90% within just a few months [2]. This means your team spends less time fixing errors and more time focusing on productive work. To tackle these challenges effectively, automated tracking tools are the way forward.

Use RFID and Barcode Scanning

RFID and barcode scanning technology turn every piece of metal into a fully traceable asset. When stock arrives, you scan it. When it moves to the cutting bay, you scan it again. Every movement is logged in real time, ensuring complete traceability - something that’s vital for industries like defence or aerospace, where compliance is non-negotiable [4].

The right hardware makes all the difference. Metal shops are tough environments, so you need rugged mobile devices that can handle dust, grease, and high temperatures. Industrial-grade scanners and tablets are built for these conditions and won’t let you down, even if they’re dropped near a plasma cutter [4]. Pair these devices with mobile printers to create on-the-spot labels, so production keeps moving without delays.

Once your physical inventory is tracked accurately, the next step is to connect this data with your existing ERP system.

Connect with Existing ERP Systems

You don’t have to throw out your current ERP system to achieve real-time inventory tracking. Tools like GoSmarter work alongside legacy systems, acting as a “production-floor source of truth” [1]. They feed cleaner, more detailed data back into your ERP via API or CSV exports. While your ERP focuses on big-picture financials, GoSmarter handles the nitty-gritty details - like tracking which offcut is stored on which rack and linking mill certificates to the correct batch.

This layered approach saves you the cost and disruption of replacing your ERP while still giving you the real-time visibility you need. As GoSmarter explains:

GoSmarter’s inventory data is more current and more granular than what the ERP typically holds [1].

Step 2: Use Real-Time Analytics to Improve Inventory

Once you’ve got digital tracking sorted, the numbers start telling you things you can actually use: which jobs are eating your margins, where stock is quietly going missing, and when you’re about to run short on a grade mid-job. Real-time analytics turn raw scans and timestamps into decisions you can act on today.

Use Data for Demand Forecasting

Real-time analytics give you a clear view of your inventory situation, including the difference between what’s physically available and what’s already allocated. Say your ERP shows 500 kg of grade 316 stainless steel. If 400 kg is already tied to active jobs, GoSmarter flags the shortage before your production schedule falls apart. These alerts also help you identify slow-moving stock or surplus inventory early, avoiding costly write-offs [1]. There is a delivery performance benefit too. When live allocation data tells your production team exactly which material is free versus committed, job sequences become predictable. On-time, in-full delivery rates improve as a direct result. Fewer emergency purchases, less over-ordering, lower stock-holding costs. Research shows that analytics powered by AI can cut lost sales by 25% and reduce excess inventory by 20% [3]. This level of insight also helps pinpoint inefficiencies on the shop floor.

Monitor Scrap Rates and Offcuts

A digital scrap logger keeps track of every piece that doesn’t end up in a finished product, helping you spot issues like poorly calibrated equipment or nesting software that doesn’t account for kerf (the width of the cut). GoSmarter’s Cutting Plans AI optimises cutting sequences against your actual stock, including remnants and offcuts. Long-products processors typically see scrap reductions of 20–50%, depending on product mix and starting baseline [6]. It also promotes offcut reuse, allowing you to check for leftover materials before placing new orders [6]. For instance, instead of ordering a fresh 6-metre bar, you can see if a 2-metre offcut from a previous job will do the trick. This not only saves money but also minimises waste, cutting down on carbon emissions by making better use of what you already have [1]. The environmental numbers are meaningful: producing a tonne of steel generates roughly 1.85 tonnes of CO₂e [14]. Recovering that tonne from scrap rather than new production saves approximately 1.4 tonnes of CO₂e. A metal shop that cuts its scrap rate by 20 tonnes per year (a realistic outcome for a mid-size long-products processor) avoids roughly 28 tonnes of CO₂e annually. That’s a board-level number, not just an operational one.

Implement FIFO and Heat Code Traceability

With real-time analytics in place, enforcing process standards like FIFO (First In, First Out) becomes much easier. FIFO prevents older stock from sitting idle and turning obsolete. Automated systems flag older inventory for use first, helping you avoid the discrepancies that can arise with manual tracking [1].

Another critical area is heat code traceability, especially in industries where compliance is a must. Each piece of metal needs a detailed history - grade, heat number, properties, and composition. Manual tracking often leads to lost PDFs or errors in heat codes, which can be a nightmare during audits. GoSmarter’s MillCert Reader uses AI to pull data from those clunky PDF mill certificates and link it directly to stock items upon receipt. This ensures full traceability without the hassle of manual entry [1][5]. By automating this process, production teams save over 120 hours per year [6] and can instantly retrieve mill certificates for customer inquiries or regulatory checks. MillCert Reader also flags anomalies automatically — certs where the reported yield strength falls outside the ordered spec, heat numbers that don’t match the purchase order, or non-standard multi-page formats that trip up manual entry. Non-conformances are raised before the material reaches the cutting bay, not after it’s been processed.

Step 3: Give Teams Mobile Access to Real-Time Updates

Tracking data is useless if your team still has to walk to a PC to check it. Put the data in their pocket. That’s what Step 3 is about.

Equip Shop Floor Teams with Real-Time Data

With mobile barcode scanning, material usage is logged directly at the workstation. No more running back and forth to jot things down manually - a process prone to errors that often lead to stock mismatches [2]. Barcode scanning is not only faster (4–7× quicker than manual entry) but also significantly more accurate [7]. As Ashley Taylor, Product Manager at Cleverence, puts it:

Running a modern fabricated metal products operation without real-time inventory visibility is a shortcut to chaos [2].

Mobile dashboards further streamline operations by offering instant access to stock levels, committed quantities, and heat codes for procurement, production, and sales teams. This eliminates outdated manual logbooks. Many mobile systems can be operational within a day, and full ERP integration typically takes just one to two weeks [1][2]. With these tools, inventory discrepancies can drop by over 90% within just a few months [2]. Plus, this real-time access ensures smooth coordination across multiple locations.

Manage Inventory Across Multiple Locations

For businesses operating across multiple sites, mobile access becomes essential. Cloud-based systems consolidate data from all locations, offering a single, unified view of inventory. Whether it’s stock at the main workshop, overflow warehouse, or in transit, you’ll know exactly where everything is [1][8]. Each transfer is timestamped, creating a clear digital audit trail [1][7].

Even in areas with poor connectivity, offline-capable mobile apps keep things running. These apps log transactions locally and automatically sync them once the connection is restored, ensuring no delays in tracking material picks [7][8].

Mobile inventory management puts real-time control in your team’s hands [7].

Common Mistakes When Implementing Real-Time Inventory

Metal shops often trip up in two key areas: picking overly complex technology and underestimating how loudly the shop floor will push back when you hand them a new system. Here’s how to avoid both.

Keep Technology Simple

A common error is treating real-time inventory like a massive IT overhaul with a lengthy setup. Shockingly, nearly 40% of companies still don’t use mobile computers or barcode scanners for inventory [12]. Many off-the-shelf systems miss crucial features like mill cert tracking or heat number traceability. Instead of simplifying workflows, these tools can create more work, forcing teams to juggle spreadsheets alongside the new system. When implementation drags on, frustrated employees often return to their old habits.

The solution? Opt for systems that require minimal setup. GoSmarter Inventory Lite lets teams upload existing stock data from spreadsheets and start tracking immediately — no consultants, no drawn-out IT projects [1]. Getting the technology right is only half the battle, though. The human side matters just as much.

Getting Your Team On Board

People will only embrace new systems if they clearly make their jobs easier. If a tool feels like extra work, it will be seen as a burden. Consider this: manual processes achieve 76% accuracy and take about 2.5 hours for order processing, while real-time systems boost accuracy to 98.7% and cut processing time to just 18 minutes [11].

The key is to lead with what’s in it for the person doing the scanning. Show them it means:

• No more hunting for “lost” stock
• No end-of-shift manual counts
• Fewer discrepancies to explain to the boss

Start small with a pilot programme in one product line or warehouse section, which allows you to iron out any issues before a full-scale rollout. Appoint respected team members as internal champions to help guide their colleagues through the transition.

Incentives should align with operational goals. If purchasing teams are rewarded for buying in bulk, they’ll keep doing it — even if it creates excess stock that ties up cash [9]. Tie scrap reduction and reorder accuracy to real numbers — hours saved, margin recovered, stock-outs avoided. People change behaviour when they can see the score [10]. Once workers see the system cuts their end-of-shift paperwork in half, they stop pushing back.

GoSmarter Tools for Real-Time Inventory Management

GoSmarter is a metals AI toolkit that sits on top of the systems you already have — your ERP, your spreadsheets, your email-based order intake — and adds the real-time visibility and optimisation those systems weren’t built to provide. No rip-and-replace. No lengthy IT project. Just the layer of intelligence your operation is missing.

From Manual Processes to AI Automation

GoSmarter replaces the clipboard, the PDF hunt, and the end-of-day spreadsheet scramble. All of it. Real-time mobile updates make it the production floor’s central source of truth — more current and more granular than anything your ERP holds. Most teams are up and running within a day.

What makes it different from a generic inventory platform is that it’s built around how metal actually moves. Bars, plate, coil, tube — multiple grades, multiple dimensions, mixed units of measure on the same order. The Cutting Plans AI knows what a remnant is, why kerf loss matters, and when a 2-metre offcut from last week’s job is the right answer for today’s rush pick. Planners stay in control of every recommendation — any AI suggestion can be overridden and replanned in seconds.

Take Midland Steel as an example. By adopting AI-driven planning, this top rebar supplier cut scrap rates by 50%. Tony Woods, CEO of Midland Steel, put it directly:

Smart technology choices can have a direct, measurable impact on reducing carbon emissions in steel manufacturing. The integration of AI and digital tracking has significantly improved our operational efficiency and sustainability performance. [6]

Another standout feature is the MillCert Reader, which saves over 120 hours annually. It automatically extracts critical details like grade, heat number, and mechanical properties from mill certificates and links them to stock items upon receipt.

Manual vs. GoSmarter: A Quick Comparison

GoSmarter’s tools are built for quick deployment and come with flexible pricing tailored to your inventory needs. Plans start at £275/month (£3,300 billed annually) for mill certificate tracking, up to £1,000/month (£12,000/year) for fully AI-optimised cutting plans. Plus, free tools like the Scrap Rate Calculator let you explore your potential ROI before committing. When it comes to profitability, knowing your exact inventory is non-negotiable.

Ready to Stop Guessing What’s in Your Yard?

Modernising your inventory system isn’t just a nice-to-have - it’s a game-changer. As GoSmarter puts it, “If you don’t know what metal you have, you’re losing money” [1]. Real-time inventory systems take the guesswork out of the equation. Say goodbye to manual stock counts, endless record searches, and production delays caused by missed reorders. With instant visibility, you can cut down on excess stock costs and keep production running smoothly.

The numbers speak for themselves. Take Midland Steel: they slashed scrap rates by 50% by switching from manual cut planning to GoSmarter’s AI-generated cutting sequences. For a typical long-products processor, a 20–50% scrap reduction is achievable within the first quarter, depending on product mix and starting baseline [13]. That’s not just a margin improvement. It frees up tonnage that was previously written off and cuts reorder costs at the same time. Properly tracking offcuts and optimising material usage doesn’t just boost your margins. It also reduces carbon emissions, a critical consideration in an industry where every tonne matters.

GoSmarter turns inventory chaos into clarity. Whether you opt for the MillCert Reader at £275/month or dive into full AI-optimised cutting plans, the return on investment is both measurable and immediate [13]. Most teams are up and running within a day by importing existing stock via spreadsheets or connecting through an API to work alongside legacy ERPs [1][6]. Real-time analytics and mobile access mean you know what’s happening on your shop floor before it becomes a problem.

You already know the spreadsheets aren’t working. The only question is how many more mis-picks it takes before you fix it. Most teams are running GoSmarter within a day.

Start for Free →

Frequently Asked Questions

Here’s the hard truth: 323 hours lost annually to unplanned downtime. That’s the average. And with 72% of factory tasks still being done manually, inefficiencies are hiding everywhere.

The fix? Lean 4.0. By combining lean principles with modern tools like AI and IoT, you can stop reacting to problems and start preventing them. AI systems now pinpoint inefficiencies with up to 95% accuracy, slash downtime by 20%, and cut maintenance costs by 10%.

The Old Way vs. The Smart Way

Instead of drowning in spreadsheets or playing catch-up, modern tools let your factory run smoother, faster, and with fewer surprises. Let’s break down how these tools work and why they’re changing manufacturing forever.

The Future of Lean: AI-Driven Process Optimisation

1. Traditional Lean Manufacturing Methods

Lean manufacturing, as it was originally conceived, thrived in a world of clipboards and stopwatches. Back then, production processes were straightforward, and tracking them was manageable. The “Visual Factory” method was at the heart of these systems, relying on tangible signals like Andon lights, which flashed red to indicate problems, or Kanban cards, which kept inventory flowing. Managers would conduct Gemba walks, physically observing the shop floor to identify inefficiencies rather than relying on second-hand reports [9][1]. The entire philosophy revolved around exposing and eliminating waste wherever it hid.

Visibility

In traditional lean systems, visibility meant making everything on the shop floor obvious and easy to monitor. Andon systems, for instance, used lights or boards to alert teams to problems, empowering operators to stop production immediately when something went wrong [9]. Kanban cards were another visual tool, triggering inventory replenishment without the need for complex systems [9][1]. The 5S methodology ensured workspaces were organised and defects were impossible to ignore [1]:

• Sort — remove anything that doesn’t belong
• Straighten — a place for everything, everything in its place
• Shine — keep it clean enough that problems are visible
• Standardise — document the right way so everyone does it the same
• Sustain — don’t let it slip

As Lean Production explains:

“Visual Factory makes the state and condition of manufacturing processes easily accessible and very clear - to everyone” [9].

However, these methods had a major shortcoming: they only provided a snapshot of what was happening at a given moment. Problems that emerged between observations often went unnoticed [11]. While the visual tools were effective, they couldn’t capture everything, leaving gaps in waste detection.

Waste Detection

Traditional lean relied heavily on manual methods to identify waste. The eight wastes — summarised by the acronym DOWNTIME — were the framework [1][11]:

• Defects
• Overproduction
• Waiting
• Non-utilised talent
• Transportation
• Inventory
• Motion
• Excess Processing

Tools like Value Stream Mapping helped map inefficiencies. Poka-Yoke devices prevented errors at the source [9][1]. Despite these efforts, manual inspections often missed subtle issues [4].

As Rish Gupta, CEO of Spot AI, explains:

“The limitation isn’t just finding waste - it’s capturing evidence of inefficiencies that occur between Gemba walks, across multiple shifts, and in areas where manual observation simply can’t scale” [11].

This dependence on human observation meant that by the time anyone spotted the problem, it had already cost real money.

Decision-Making Speed

Traditional lean systems often left managers playing catch-up. Decisions were typically based on past reports rather than live data. By the time an issue was identified, it had already caused significant disruption [2][12]. For example, at Precision Components Inc., a Midwest automotive supplier, managers struggled to locate specific orders on their sprawling 7,000-square-metre factory floor. Until mid-2024, they relied on paper-based systems, which failed to catch issues like tool wear until entire batches were ruined. This resulted in an 18% scrap and rework rate and a bloated 28-day lead time [13].

Without real-time data, decision-making often relied on the intuition of experienced operators — what some call “tribal knowledge” [2][13]. Root cause analysis could stretch out for weeks or even months, further delaying corrective actions [11]. That slow response time exposes the real limits of traditional lean.

Scalability

Scaling traditional lean practices was another major hurdle. While Standardised Work documented best practices, ensuring consistent application across multiple shifts was a constant challenge [9][10][11]. Stopwatch-based time and motion studies, though helpful, were laborious, prone to errors, and impractical for analysing thousands of cycles across different operators [4][11]. Manual processes and frequent downtime made it difficult for operations to grow efficiently. These scalability issues have driven many manufacturers to adopt modern, data-driven solutions that can handle complexity more effectively.

2. Data-Driven Lean Manufacturing Tools

Modern lean manufacturing has evolved beyond traditional manual methods, introducing data-driven tools that reshape how factories operate. These tools act like a “digital nervous system”, monitoring machines, operators, and processes in real time. The goal isn’t to replace lean principles but to automate the tedious tasks, allowing teams to tackle waste before it spirals into costly problems.

Visibility

Instead of relying on periodic observations, data-driven tools provide live, continuous monitoring. With the help of Industrial IoT sensors and AI dashboards, factories now have a “Digital Gemba” — a virtual version of shop floor observation. This technology lets managers track metrics like Overall Equipment Effectiveness (OEE), cycle times, and throughput in real time, even remotely.

For instance, in 2024, Versatech, an automotive supplier, adopted a real-time production monitoring system from Mingo Smart Factory, boosting its OEE by 30% [6]. Since 72% of factory tasks are still manual [1], modern platforms extend visibility to manual workstations through digital job routing and scheduling. This breaks down silos between production, maintenance, and quality teams, ensuring everyone works with the same accurate data.

Waste Detection

AI has turned waste detection into a continuous process rather than a periodic audit. AI-based anomaly detection can identify inefficiencies with an accuracy rate of 92–95% [4]. At Toyota’s Kentucky plant, AI inspection systems reduced defect rates by 91% by spotting subtle issues invisible to the human eye [4]. These systems process huge amounts of data, alerting operators to problems and pinpointing their root causes before they escalate.

A great example comes from H&T Waterbury, a metal stamping company that integrated its monitoring system with Fiix in 2024. This let them implement condition-based maintenance, slashing unplanned downtime by 71% [6]. Sadia Waseem from Retrocausal explains this shift perfectly:

“AI creates an eighth dimension beyond Lean’s traditional seven wastes, which is unused information” [4].

Decision-Making Speed

Traditional methods often react to problems after they’ve occurred. Data-driven lean catches issues before they blow up. AI-powered demand forecasting systems, for example, can reduce forecasting errors by 20–50% [4], helping manufacturers avoid material shortages or excess inventory. Similarly, AI-assisted Root Cause Analysis (RCA) can cut the time engineers spend on data preparation by 50–70% [14], allowing faster resolution of issues.

Real-time alerts let teams intervene before defects occur or equipment fails. Syed Ajmal, Senior Solutions Engineer at MathCo, explains:

“The factories that will win the next decade are not the ones with the most automation, they are the ones that learn the fastest. Lean AI makes that possible” [7].

Scalability

Data-driven tools also make scaling operations easier by converting “tribal knowledge” into digital work instructions that update automatically based on performance data [4]. Cloud-edge hybrid systems — combining cloud computing with local processing — allow AI models to scale across multiple facilities while maintaining the speed needed for production lines [15].

For example, a medical device manufacturer reduced its scrap rate by 60% by deploying an AI-driven “assembly copilot” across four workstations [4]. Similarly, platforms like GoSmarter simplify complex tasks for metals manufacturers, such as reading mill certificates, calculating scrap rates, and scheduling production runs. GoSmarter connects directly to your existing ERP, shared drives, and email — it sits on top of what you already use, rather than replacing it. These Lean 4.0 platforms can cut unplanned downtime by up to 70% and maintenance costs by 25% [3], proving that scaling up doesn’t have to come at the expense of efficiency or profitability.

Strengths and Weaknesses

Traditional lean manufacturing methods and modern data-driven approaches are increasingly moving in different directions. The old-school methods — relying on whiteboards, clipboards, and manual observation — can work well for simple production lines. But as operations grow more complex, “invisible bottlenecks” start to appear, and managers can spend hours trying to track down stuck orders on the shop floor [13]. In contrast, data-driven tools use real-time dashboards and IoT sensors to cut response times drastically — from hours to just minutes. For example, shift handovers that once took 30 minutes now take five [13]. The table below highlights how these approaches differ.

These operational upgrades lead to measurable financial benefits. For instance, Precision Components Inc., a manufacturer with 150 employees, reduced material waste by 22%, saving $180,000 annually. They also cut lead times from 28 days to 21 days after adopting IoT vibration sensors and a manufacturing execution system between 2024 and 2026 [13]. Similarly, a medium-sized UK fabrication company achieved a first-year ROI of £15,000 on a £9,000 software investment. They also saved £16,250 annually by adjusting housekeeping schedules and cut energy costs by an extra £6,500 each year [8].

The difference in scalability is especially striking. Traditional lean methods struggle when production variables multiply — human observers simply can’t keep up with every detail across multiple shifts. Data-driven platforms like GoSmarter step in to handle these challenges. They automate tedious tasks like reading mill certificates, calculating scrap rates, and scheduling production, freeing engineers to focus on innovation instead of repetitive data entry. H&T Waterbury is a direct example from within metals: the metal stamping company integrated condition-based monitoring into their maintenance workflow and cut unplanned downtime by 71% [6] — proof that data-driven lean in metals doesn’t require a billion-pound R&D budget, just the right tool pointed at the right problem. Deloitte sums it up perfectly:

“Digital lean provides an opportunity to target hidden components of waste, such as information asymmetry and latency, that often go unnoticed” [2].

That’s why more manufacturers are ditching the guesswork and letting AI do the heavy lifting.

The Numbers Make the Case

The case for a digital overhaul in manufacturing is clear. Traditional lean methods are no longer enough to keep pace. Data-driven tools speed up operations. They close the gap between what ERP systems plan and what actually happens on the shop floor. With so many processes still handled manually [16], the opportunity to cut waste, boost uptime, and avoid errors is enormous.

The results speak volumes. Carolina Precision Manufacturing, for instance, saved £1.5 million in just one year by using an IoT platform to improve operator accountability [16]. These aren’t minor tweaks — ditching manual record-keeping for real-time, data-powered systems is what made those results possible [16].

One medium-sized UK fabrication company put £9,000 into a digital lean software platform and saw £15,000 back in year one — plus £16,250 in ongoing annual savings and £6,500 cut from energy costs [8]. That’s not a pilot. That’s a business case. Ready to run the same maths on your shop floor? See GoSmarter pricing.

For metals manufacturers stuck in the rut of endless spreadsheets, GoSmarter is built specifically for heavy industry. The fastest entry point is mill certificate reading: GoSmarter reads a PDF mill cert in under 30 seconds — a task that can eat 20 minutes or more of an engineer’s time when done by hand. Most customers are live in under a day, with no IT project required and no changes to existing systems. GoSmarter sits alongside your ERP and spreadsheets, adding intelligence to the processes you already run. As Tony Woods, CEO of Midland Steel, explains:

“Smart technology choices can have a direct, measurable impact on reducing carbon emissions in steel manufacturing. The integration of AI and digital tracking has significantly improved our operational efficiency and sustainability performance.”

Start small — pilot digital upgrades on a few machines, measure the ROI, and scale from there [8]. Focus on the biggest bottleneck first, whether it’s a machine or a process, and target improvements there [9]. Shifting from reactive to predictive maintenance isn’t just about saving time. In this industry, every penny counts — and waste is expensive.

The future of manufacturing belongs to those who stop guessing and start measuring. Turn your data into your edge.

The fastest way in? Start with mill certificates. GoSmarter reads PDF mill certs in seconds — try the Mill Certificate Reader free.

FAQs

Here’s the truth: your shop floor doesn’t need more spreadsheets or yesterday’s data. What you need is real-time visibility. AI tools now make it possible to track every raw material, order, and machine status as it happens. The result? No more hunting for heat numbers or scrambling to fix production delays.

The Old Way vs. The Smart Way

Stop running your factory like it’s 1985. Let’s break down how AI tools can eliminate the chaos and give you full control over your floor.

See It in Action: Real-Time Shop Floor Control

Step 1: Track Raw Materials in Real Time with Automated Sensors

Start with AI-powered sensors to track raw materials in real time. They monitor movement through receiving, storage, and picking — feeding live data straight into your system [5]. Retrofit IoT sensors — vibration, current, proximity, photoelectric — and even your oldest kit gets connected [4]. Pair them with AI-powered Optical Character Recognition (OCR) to digitise essential documents instantly.

Digitise Mill Certificates with AI OCR

Mill certificates are often the bane of production managers. They arrive as messy, inconsistently formatted PDFs, requiring someone to manually extract key details like heat numbers, chemical compositions, and mechanical properties. GoSmarter’s MillCert Reader eliminates this tedious task in just 5–15 seconds per page [6]. Simply upload the PDF, and the AI extracts and links critical data - like heat codes, grades, and yield strength - directly to your inventory records [1][6].

Take Midland Steel, for example. In December 2024, this UK-based rebar manufacturer implemented the MillCert Reader. Previously, the team spent hours manually entering product codes and chemical compositions. With the AI tool, they saved 10 hours per month and eliminated manual errors in renaming and data entry [8]. As their Production Manager explained:

“I logged in for the first time and was up and running in minutes. MillCert Reader now pulls all the key info - chemical composition, mechanical properties - automatically. What used to take hours every week is done in seconds.” [8]

The tool even renames certificate PDFs with heat numbers and grades automatically, so you’re never stuck searching through files labelled “cert1.pdf” when you need compliance data [1]. Plans start at £275 per month, with a free trial available [1].

Cut Manual Errors with Real-Time Monitoring

Digitising documents is just the beginning. Real-time monitoring also removes manual errors across your operations. Mistakes often happen during manual checks - like misreading a heat number at goods-in, which can lead to the wrong material entering production. Automated sensors prevent this by continuously validating your physical stock against system records. Autonomous robots can scan up to 10,000 pallet locations per hour, achieving near-perfect accuracy compared to the 91% typical of manual checks [7]. Rory Fidler, Vice President Cargo Technology at Menzies Aviation, highlighted the impact:

“Mimi [the robot] is delivering this, as on a daily basis we are scanning over 500 locations and achieving high accuracy levels in a fraction of the time it has historically taken to do it manually.” [7]

For metals manufacturers, heat codes entered during the “Goods In” process automatically link to digitised certificates, creating an instant and reliable audit trail [6]. Need material with specific yield strength for a job? Your dashboard verifies compliance in seconds, sparing you the hassle of digging through physical files. Real-time monitoring can improve production efficiency by up to 29% within the first week [4].

Step 2: Use Predictive Analytics to Prevent Shortages and Waste

With real-time tracking in place, predictive analytics sharpens your inventory management. It moves you away from the risks of overstocking, which ties up cash, or shortages, which lead to missed deadlines and costly emergency orders. Instead, machine learning forecasts what you’ll need and when, while ensuring materials are used efficiently.

Forecast Inventory Accurately

Predictive analytics dives deeper into your inventory needs by combining historical data with real-time insights.

AI-powered forecasting replaces guesswork with precise, data-driven predictions. By analysing past sales and inventory trends alongside external factors - like raw material prices, weather changes, economic conditions, and even social media trends - it creates highly accurate demand forecasts [9][13]. Advanced machine learning algorithms uncover patterns and relationships in massive datasets, providing detailed forecasts down to the SKU or store level [9][11][13]. Unlike traditional methods, these AI systems update predictions almost instantly as new data flows in, allowing you to adjust production schedules on the fly [10][13].

The data backs this up: AI forecasting can reduce errors by 20% to 50% and cut stockouts by up to 65% [9][13]. Businesses using generative AI for inventory management in late 2024 reported cost savings exceeding 10% [13], while 43% of companies still lose sales due to poor forecasting [10]. To maximise these benefits, ensure you have at least 12–18 months of clean, structured historical data before training your AI models [10]. Also, integrate forecasting tools with your ERP, POS, and warehouse systems to avoid data silos and enable real-time updates [10][12].

Cut Scrap with Smart Calculations

Optimising your supply chain is just one side of the coin - smart calculations help tackle material waste.

Scrap can eat into profits quickly. Even a small 2–3% reduction in scrap waste can save high-volume plants hundreds of thousands of pounds annually [14]. Predictive analytics powered by AI can reduce scrap by 12–20% by identifying and addressing process inefficiencies before they escalate [15][16]. For example, GoSmarter’s Rebar & Scrap Optimiser calculates cutting patterns to minimise waste and tracks offcuts, reducing both material costs and carbon emissions. Instead of relying on manual cutting plans, the tool generates optimised plans that sync with your inventory and orders.

An improvement of just 1% in First Pass Yield (FPY) can reduce overall manufacturing costs by as much as 4% [17]. In the metals industry, using AI to cut scrap waste not only boosts profits but also aligns with sustainability goals.

Tony Woods, CEO of Midland Steel, highlighted the impact of these technologies:

“Smart technology choices can have a direct, measurable impact on reducing carbon emissions in steel manufacturing. The integration of AI and digital tracking has significantly improved our operational efficiency and sustainability performance.” [3]

Step 3: Monitor Production Live with Smart Dashboards

Once automated tracking and forecasting are in place, move to live monitoring. Smart dashboards pull from MES, ERP, PLCs, and even spreadsheets — giving you live insights refreshed by the minute [18]. Every critical metric, visible, in one place.

Bring All Your Data Together

Factories often rely on a jumble of systems - production data here, inventory there, and quality certificates either buried in filing cabinets or scattered across email threads. This lack of organisation can make it tough to get a clear picture and increases the risk of poor decisions. GoSmarter’s dashboard acts as your single source of truth. It connects directly to your existing systems. It even consolidates certificate details, so you can see not just your total stock but also what’s already allocated to active orders [2]. Plus, built-in search tools make finding specific items quick and painless [19].

Use Live Data to Make Smarter Decisions

With everything centralised, your dashboard becomes the nerve centre for decision-making. Real-time updates mean you can spot and address issues as they happen. For example, instead of waiting days to notice a rise in scrap rates, your dashboard alerts you immediately. Using natural language processing, you can ask straightforward questions - like why scrap rates are spiking on Line 2 - and get instant, data-backed answers [18]. By focusing on a few key metrics like Overall Equipment Effectiveness (OEE), Cycle Time, Scrap Rate, and First Pass Yield, the dashboard stays clean and easy to navigate [18]. Features like automated reorder alerts also help you avoid stockouts. Most teams can get real-time inventory tracking operational in just one day [2]. Plus, with GoSmarter’s “start for free” model, you can scale up as your needs grow [3].

Tony Woods, CEO of Midland Steel, shared how integrating AI and digital tracking gave his team real-time inventory visibility tied directly to mill certificates. This shift not only improved operational efficiency but also boosted sustainability efforts [2][3].

Step 4: Improve Scheduling and Production with AI Tools

Once you’ve got live dashboards feeding you real-time floor data, the next move is to ensure production flows smoothly into the next phase. This is where AI-driven scheduling steps in, turning raw data into actionable plans. Forget the chaos of whiteboards or sluggish ERP systems - AI slashes planning time from days to minutes and adapts instantly when disruptions hit [20].

With scheduling sorted, the focus shifts to making better use of materials and maintaining production consistency.

Create Better Cutting Plans

GoSmarter’s Smart Production Scheduler takes the guesswork out of cutting plans. Instead of manually crunching numbers or gambling on which offcuts to use, the AI evaluates stock levels and current orders to calculate the best 1D cutting patterns. Take 2023, for instance - Blount Fine Foods, managing a hefty 1,500 SKUs under Sr. Director Jonathan Wells, used AI scheduling to cut finished goods waste by 35% and improve production efficiency by 2% simply by reducing changeovers [22]. For metals manufacturers, this translates to less scrap, lower material costs, and fewer carbon emissions. In fact, the system can trim scrap waste by up to 50%, saving money while aligning with sustainability goals.

Meet Deadlines Consistently

AI-powered scheduling does more than optimise cutting plans — it keeps your entire operation running on time. When machine breakdowns or rush orders hit, the system recalibrates instantly [20][21]. No costly delays. Companies using AI for production scheduling report up to a 30% boost in operational efficiency and a 25% improvement in on-time deliveries [21]. Take Atria, a major meat supplier in Finland. Under SVP Tapani Potka, they hit 98.1% weekly forecast accuracy. They also cut manual adjustments by 13% — freeing planners to handle exceptions instead of babysitting spreadsheets [22]. For metals manufacturers with tight tolerances and demanding deadlines, that precision matters. Combined with real-time floor monitoring, AI scheduling gives you complete control over your operations.

Step 5: Integrate Your Tools for Complete Floor Control

Real-time dashboards and smart scheduling are powerful on their own — but they get even better when they talk to each other. Most factory software lives in silos. Your inventory system doesn’t speak to your cutting planner. Your ERP has no idea what’s happening on the shop floor. Integration fixes that. Data flows without manual copying, data entry, or lost records. Connected tools mean no blind spots.

Combine Tools for Better Efficiency

GoSmarter’s tools are built to work together. For example, the MillCert Reader attaches certificate data directly to inventory records, which then feed into the Optimisation tool to create cutting plans based on actual stock levels - no need for manual data entry or guesswork [2][24]. No manual entry. No copying. No wasted time.

Tony Woods, CEO of Midland Steel, shared how integration transformed their operations in February 2026:

“The integration of AI and digital tracking has significantly improved our operational efficiency and sustainability performance.” [3]

By linking mill certificates to real-time inventory, Midland Steel reduced administrative burdens and made smarter material choices, which in turn helped lower carbon emissions. Similarly, Tadhg Hurley, Managing Director of MAAS Precision Engineering, highlighted the benefits of embracing advanced tools:

“We’re constantly seeking ways to improve our systems and processes with technology, and this has been a great opportunity to accelerate our adoption of smarter tools that open up new opportunities.” [3]

GoSmarter connects to your existing ERP and MES systems without disrupting how you work [23][2]. You can ease into integration with a phased approach:

• Crawl phase: Start with the independent web interface to familiarise your team with the core features.
• Walk phase: Progress to semi-manual CSV imports and exports for periodic data sharing.
• Run phase: Achieve full automation with REST APIs for real-time, bidirectional data sync - orders move from your ERP to the AI planner, while optimised cutting plans flow back to production tablets.

REST APIs are included at no extra cost, offering real-time synchronisation without hidden fees [23].

Compare Plans to Find Your Best Option

GoSmarter offers flexible plans to suit different needs, whether you’re starting small or managing large-scale operations. Here’s a breakdown of the options:

Just getting started? GoSmarter Insights is free and gives you instant calculations for scrap and carbon emissions. If compliance is a priority, Product Lineage automates mill certificate scanning and links data to heat codes. Manufacturers needing comprehensive inventory and order control will find Business Manager invaluable. And for high-volume operations with complex cutting schedules, Production Planner delivers AI-driven plans that slot straight into your systems.

Conclusion: Gain Real-Time Control Over Your Factory Floor

The difference between a factory that runs like clockwork and one constantly battling chaos often boils down to one thing: visibility. When you can see everything on your floor — every stock location, every order status — you stop firefighting and start running things properly. GoSmarter’s AI toolkits make this level of real-time insight part of your everyday workflow.

Start by introducing real-time inventory tracking to cut down on wasted time searching for materials and prevent over-ordering scattered stock [2]. Use AI-powered OCR to digitise mill certificates in seconds, and take advantage of predictive analytics to spot material shortages before they disrupt production. Smart dashboards pull all your data into one place, giving you a clear, up-to-date picture far beyond what traditional ERP reports can offer [2][26]. With these tools in place, you’re not just seeing more — you’re cutting waste and saving real time.

Here’s proof it works. Manufacturers using AI and digital tracking report significant gains in efficiency and performance. For example, Beshay Steel reduced unplanned downtime by 47% and saw a return on investment in just 4.2 months. JSW Steel saved an incredible 2 million man-hours annually by digitising their supply chain processes. These examples show how adding AI tools to your existing systems delivers results faster than overhauling your entire ERP setup [25].

GoSmarter’s AI tools bolt onto your current systems. No long rollouts. No hidden enterprise costs. You can even get started for free with GoSmarter Insights [3]. By layering AI over your legacy systems - beginning with real-time inventory tracking - you move from reactive guesswork to proactive, data-driven control. Say goodbye to manual processes and unwanted surprises, and let live data guide your factory to peak performance.

FAQs

4,000 Workers in Scunthorpe Just Had a Very Good Week

The agreement is a turning point for British Steel. Chief Executive Allan Bell called it a “record-breaking contract” — and he wasn’t being modest. This deal directly backs British Steel’s 4,000 employees and the wider supply chains that depend on them.

“This is a record-breaking contract for British Steel and a major boost to our 4,000 employees and many more people in our supply chains”, said Bell. “After government intervention last April, everyone at British Steel has worked hard to stabilise the company. This deal represents us moving from stabilisation to building long-term sustainability for the business.”

The contract stands out not only for its size but also for its backing by UK Export Finance (UKEF) — the largest such order ever secured with UKEF support. Bell added: “As one of the largest ever orders for billet in the history of this company, it marks a tremendous vote of confidence in British Steel and UK manufacturing. And as the biggest order we have ever secured with UK Export Finance, it demonstrates how we are working with the UK Government to meet the global demand for our products.”

Ports That Haven’t Been Touched Since the 1970s. Not For Much Longer.

The project aims to modernise critical port infrastructure in Nigeria. Ronald Chagoury Jr., Vice-Chairman of Hitech Construction Africa Ltd, put the scale of the challenge plainly: “Tin Can Island and Lagos Apapa ports are currently at a critical stage, as they have not undergone any significant rehabilitation since they were originally built in the mid-to-late 1900s. Our objective today is to give them a new life for at least the next 50 years, while significantly increasing their capacity and enabling them to accommodate larger vessels, faster turnaround times, and higher volumes of trade, positioning Nigeria as the regional leader in maritime logistics and supporting the country in unlocking its trillion-dollar economy.”

British Steel’s 140mm rebar-type billets are a semi-finished steel product — the raw building block that goes into rebar, reinforcement, and structural works. Built to last. Shipments begin this spring and run for three years.

When Government Backing Actually Delivers Something Real

Business and Trade Secretary Peter Kyle praised the deal: “Hot on the heels of our landmark Steel Strategy, this is a major win for British Steel made possible by UK Export Finance which is testament to the quality of UK-made steel and the booming UK-Nigeria relationship.”

Tim Reid, CEO at UK Export Finance, was direct: “This deal represents a milestone for UK-Nigeria trade relations and demonstrates the full capacity of UK Export Finance to unlock transformational opportunities for British businesses, while supporting sustainable economic growth in key markets.”

Craig Harvey, British Steel’s Commercial Director for Semi-Finished Products, wasn’t short on confidence: “Our capacity and capability ensure we offer a unique solution to the developers of major infrastructure projects, and this contract underlines our world-wide reputation for delivering market-leading products with first class logistics. We’re delighted to have secured this order and look forward to supporting this exciting development.”

The project is expected to direct over £200 million back into the UK economy.

Two Major Export Wins in Two Months. British Steel Is on a Roll.

This is the second major export contract British Steel has secured in recent months. In February, the company announced another significant order — worth tens of millions of pounds — for a high-speed railway project in Türkiye. Two wins. Two months. Both large-scale infrastructure projects, both backed by government financial tools.

British Steel’s leadership see this as a vital step toward long-term sustainability. And as a signal that UK manufacturing can still compete on the global stage, it’s a compelling one.

What a Production Surge Means for the Rest of the Industry

When a major steelmaker ramps up, the pressure doesn’t stay at the top. It flows down. Service centres get busier. Fabricators face tighter lead times. Stockholders have to manage larger, faster-moving inventory.

Somewhere in that chain, a production manager is trying to do all of this with software built in 2015.

More throughput with the same tools doesn’t give you more output. It gives you more chaos.

The companies that benefit from the next wave of demand are the ones with their operations under control. That means knowing your yield before you cut. Reading your mill certificates in seconds, not minutes. Planning your nesting runs without calling in a favour from whoever “knows how the software works.”

That’s exactly what GoSmarter was built for. Start for free →

Read the source

The announcement follows urgent warnings from Tata Steel in South Wales about the risk of plant closures without government intervention. During a visit to Tata Steel’s Port Talbot site, Business Secretary Peter Kyle set an ambitious target: 50% of steel used in the UK will be produced domestically, with half of that output coming from Wales.

“This is a very strident set of protections for British steel production to equal out the unfair competitive behaviour elsewhere that doesn’t create a level playing field for British steel”, said Kyle. The strategy also lines up with investments in a shift to green steel and a push to bring domestic production up to global standards.

The new rules: what’s changing in July

From July, the UK will introduce stricter import measures. Quotas on several overseas steel products will be cut by 60%. Tariffs on imports outside those quotas will rise to 50%. These measures mirror recent actions taken by the United States, European Union, and Canada — all responding to an oversupply of Chinese steel. China, the world’s largest steel producer, hit record-high exports in December, adding pressure to an already saturated global market.

These measures also land just as the old steel safeguards expire — the ones put in place before the UK left the EU. The EU has proposed the same move: doubling its tariffs to 50% and cutting quotas for imports from third countries, including the UK. Both sides are expected to negotiate carve-outs to unlock lower tariffs between them — a joint effort to tackle cheaper Chinese steel.

Reviving a shrinking industry

The new strategy protects what’s left of the UK’s steel industry after decades of decline. Port Talbot, once a hub of steel production, shut its last blast furnace in 2024. That closure happened despite a £500m government package to fund the switch to electric arc furnaces — a change that cost 2,800 jobs. Construction on the new furnaces is already underway, with operations expected to start in 2028.

The Scunthorpe plant in north-east England remains the UK’s last producer of virgin steel. The government took it into public ownership in April last year after its Chinese owner, Jingye, threatened to close the gates. Since then, taxpayers have been propping it up — and the bill is rising. Recent figures from the National Audit Office put the total cost to the public purse at over £1.5bn by 2028.

Kyle said the blast furnaces at Scunthorpe “would continue until the companies themselves decide to transition” — and said nothing about the NAO’s report.

The industry is cautiously backing the plan — for now

Despite the obstacles, industry reps are cautiously backing the plan. Alasdair McDiarmid, assistant general secretary of the trade union Community, described recent talks with ministers and Tata Steel executives in Port Talbot as “positive and productive.” He noted: “We have sat across from business secretaries for years who promise things and don’t deliver, but this government is following through … At Port Talbot we can see progress.”

Welsh First Minister Eluned Morgan also welcomed the strategy, calling it “good news for our steel communities and the thousands of people across Wales who work in or around the industry, now and in the future.”

The government has made its move. Whether it’s enough depends on execution — and on how fast domestic mills can ramp up. Energy costs remain brutal, and Chinese export volumes aren’t going away. For manufacturers, the question isn’t whether this affects you. It’s whether you’re ready.

Which steel products take the hardest hit

The tariffs don’t land evenly. Certain product families feel it first and feel it hardest.

Flat products — hot-rolled coil, cold-rolled strip, galvanised sheet — face the sharpest quota cuts. These grades feed automotive, white goods, and general fabrication lines. If you stamp, press, or roll for a living, your input costs are heading north.

Long products — rebar, wire rod, and sections — also fall within the new quota restrictions. Construction contractors and structural steel fabricators will feel the squeeze quickest. Cheap rebar from Turkey and Eastern Europe has undercut domestic supply for years. That era ends in July.

Structural steel — I-beams, hollow sections, and angles — sits right at the intersection of high demand and thin domestic supply. With Port Talbot’s blast furnaces already gone, the UK cannot replace all structural grades from home production. That gap is real and it is open right now.

Stainless and speciality grades face less direct tariff exposure — for now. But watch this space. If China redirects export volumes away from carbon flat products, speciality mills will feel the knock-on pressure on alloy inputs soon enough.

What this means for UK manufacturers right now

Your raw material costs are going up — plan for it

The 50% tariff on out-of-quota imports is not a distant threat. It starts in July. If you buy steel on the spot market, your next purchase order will look different to the last one. Buyers who locked in forward contracts before the announcement are better placed. Everyone else is playing catch-up.

If you don’t know which of your stock was bought at what cost and from where, you can’t quantify your exposure. That calculation starts with accurate, up-to-date inventory data — not last Friday’s spreadsheet.

Supply chains built on cheap imports need rethinking

Many UK fabricators spent the last decade sourcing hot-rolled coil and structural sections from Asia and Eastern Europe. That model worked when tariffs were low and freight was predictable. Neither condition holds today.

Go through your approved supplier list now. If more than half your steel volume comes from outside the quota bands, you carry serious cost exposure after July.

Lead times will stretch before they improve

New domestic capacity — including Scunthorpe’s stabilised output and Port Talbot’s future electric arc furnace — will not fill the supply gap overnight. Expect supply tightness to persist well into 2027. Scunthorpe remains under pressure, and Port Talbot’s new electric arc furnaces won’t be operational until 2028. Start ordering further ahead than you normally would.

What should manufacturers do right now

Don’t wait for an invoice shock to force your hand. Here is where to start:

• Work out which of your steel buys fall outside the quota. Break down last year’s purchases by product family and country of origin. Know your exposure before July, not after.
• Call your steel service centre this week — not in June. Ask directly about forward-priced contracts and stock availability on your core grades. The buyers who move first get the better terms.
• Build a 90-day buffer on your highest-volume grades. Domestic mill lead times are already tightening. A buffer gives you room to be selective when the market gets worse.
• Reprice any live quotes with post-July delivery dates. If you based those quotes on today’s steel costs, you may have already locked in a loss. Check every open quotation now.

Your service centre can tell you what’s available. You still need to know what you actually have — and what it cost to land it.

One more thing. If your steel stock lives in a spreadsheet right now, this market volatility will hurt you more than your competitors. GoSmarter’s Inventory Management was built for metals — not adapted from generic warehouse software. It tracks stock the way a steel business actually works: by length, grade, and heat number, not units on a shelf.

If your cost-per-tonne data is out of date, you cannot accurately reprice live quotes — and you risk locking in margin losses before the tariff even hits. See it in action →

Read the source

Lost mill certificates aren’t just annoying. They’re a compliance nightmare. When auditors demand proof for heat number 47B392, you don’t have time to dig through binders or search inboxes. Every minute spent hunting for certificates has real consequences:

• Failed audits
• Lost customers
• And in a safety-critical industry, something far worse

The problem? Paper records and Excel trackers are holding you back. They’re error-prone, slow, and unreliable. The fix is straightforward. GoSmarter’s MillCert Reader reads the cert, pulls the heat number, and links it straight to your stock — in under 15 seconds.

The Old Way vs. The Smart Way

Switching to AI isn’t just about saving time. It’s about running tighter, smarter operations. Let’s break down how it works.

Your Paper Binder System Has a Heat Number Problem

Generic OCR tools fall apart on mill certificates — they mistake “Rp0.2” for a product code instead of yield strength. GoSmarter’s MillCert Reader was built for this exact document, not PDFs in general. Trained on thousands of actual mill certificates, it distinguishes between a heat number and a batch code. It extracts chemical composition, mechanical properties, and testing methods with precision. Scanned papers, digital PDFs, blurry phone photos — the system handles all of it. Output is clean, structured, and audit-ready [6].

This Is What Upload-and-Done Actually Looks Like

Here’s how it works: upload a certificate at goods-in, and within 5–15 seconds per page, the system extracts all the essential details [1]. Heat numbers, material grades, tensile strength, and carbon equivalence are captured with precision and automatically linked to your inventory by heat code. Forget the hassle of renaming files or deciphering cryptic filenames like “47B392_final_v2.pdf.” The MillCert Reader renames documents using heat numbers and grades, so you always know exactly what you’re looking at [6].

A Production Manager shared their experience in March 2026:

“I logged in for the first time and was up and running in minutes. MillCert Reader now pulls all the key info - chemical composition, mechanical properties - automatically. Tasks that once took hours now complete in seconds.” [7]

Three Working Weeks. Back in Your Team’s Pocket.

That’s 120+ hours a year — three full working weeks — back in your team’s pocket. Based on processing around 15 certificates a week at roughly 8 minutes each, that’s over 100 hours of manual data entry eliminated per person, per year [6]. Factor in audit prep time and the number clears 120 easily. On top of that, certificate processing speeds up by 60%, and automated validation against EN 10204 standards [5] means transcription errors stop being your problem. Every piece of stock arrives with accurate, audit-ready data.

Want to see it in action? Start a free trial and watch the cert chaos disappear [6].

It Works with the ERP You’re Already Stuck With

You don’t have to overhaul your ERP or pause production. GoSmarter is built to complement your current systems, not replace them [6]. Whether you’re on a modern SAP setup or a legacy system from before EN 1090 regulations, you don’t need a consultant. You don’t need a six-month rollout. The guided setup wizard connects GoSmarter to your ERP data fields in under 30 minutes — no custom coding required.

Three Steps. Under 30 Minutes. No Consultants.

Getting started involves just three simple steps. First, install a lightweight software agent using a single downloadable package. Next, configure API endpoints through a guided wizard that identifies your ERP data fields in under 30 minutes. Finally, run an initial batch scan of your existing PDF certificates [1][2]. The system delivers 98% OCR accuracy for CE marking and ISO 9001 traceability data, and it works seamlessly with popular UK ERPs like SAP and Oracle, as well as older systems managing pre-2014 paper records [1][2][4].

GoSmarter uses universal adapters and RESTful APIs to connect with legacy systems via standard protocols like ODBC/JDBC. This means you won’t need custom coding or costly upgrades [1][4]. Its plug-and-play approach is already trusted by BSI-certified systems in the UK metals sector, ensuring smooth integration with Factory Production Control systems without requiring major IT changes [1][2]. Once integrated, your operations can shift from manual tracking to automated efficiency.

How to Switch Without Stopping Production

Start with a 7-day pilot programme: export your existing spreadsheets - such as Excel logs for consumable certifications or staff qualifications - into GoSmarter’s import tool. Then scan 100 sample mill certificates using the mobile app, allowing the AI to validate them against EN 1090-2 standards. Finally, set up automated alerts for certificate expiry dates [1][3]. This approach mirrors successful transitions at companies like Bourne Steel, where manual records were digitised without disrupting operations, achieving full traceability from raw materials to final inspection [1][3].

To ensure a smooth transition, use parallel running - operate GoSmarter alongside your current manual systems for 2–4 weeks. The dashboard syncs data in real time, so operations continue uninterrupted [2][4]. Schedule integration during off-peak hours to avoid delays in Responsible Welding Coordinator approvals, keeping everything aligned with BS EN 1090 requirements [2][4]. For older records, GoSmarter offers bulk OCR scanning for paper certificates, achieving over 95% accuracy even for faded mill certs, and supports CSV/XML imports for digital files. The AI cross-references these records against standards like material testing and welding procedures to ensure compliance [1][3].

The Numbers Don’t Lie

Manual vs. GoSmarter: Side by Side

Switching to automated certificate management with GoSmarter can save over 120 hours annually per user [6]. The MillCert Reader processes certificates in just 5–15 seconds per page [1], compared to the hours spent weekly on manual data entry. Plus, error rates drop to nearly zero, eliminating the risk of transcription mistakes [6].

These time savings and error reductions contribute to better compliance and smoother operations for metals manufacturers across the UK.

Real Teams, Real Audits, Real Results

The impact of these changes goes beyond efficiency. Manufacturers have seen their compliance processes transformed. For example, Midland Steel’s Production Manager described how the system automatically extracts chemical compositions and mechanical properties, renaming documents with heat numbers and grades in seconds:

“What used to take hours every week is done in seconds. I logged in for the first time and was up and running in minutes.” [6]

Another example comes from a UK steel stockholder who adopted GoSmarter’s AI in 2026. The team eliminated the tedious task of renaming bulk PDFs, and audit preparation shifted from days of manual work to instant, one-click reporting [5]. By automating these processes, teams can focus on production rather than drowning in paperwork, ensuring audits no longer disrupt valuable work hours.

Stop Losing Certificates and Start Preparing for Audits

Automating certificate management doesn’t just save time. It means the next audit isn’t a fire drill.

What Your Team Gets on Day One

GoSmarter’s MillCert Reader automatically extracts heat numbers and material grades, building an unchangeable audit trail that meets ISO 9001 and EN 10204 standards [6][5]. Every certificate is instantly searchable by heat number, supplier, or specification and linked directly to your inventory. No more cryptic filenames like “cert1.pdf”. No more hunting through shared drives.

When the auditors arrive, there’s no fire drill. Pull up the record by heat number. Generate the compliance report. That’s it. No rummaging through filing cabinets, no apologies. Every certificate is traceable. Every audit is ready.

Get Started with GoSmarter

Stop hunting for certificates. Start a free trial and see how fast your next audit prep gets done. Paid plans from £275/month (billed annually) or £350/month on a rolling basis [6]. Whether you’re dealing with paper certs at goods-in or need to prove traceability to a customer, GoSmarter connects to your existing ERP and delivers results from day one.

Upload your certificates, let the AI extract the data, and watch your audit prep shrink from days to seconds [5]. And you’ll never have to explain a missing certificate to an auditor again.

Frequently Asked Questions

GoSmarter’s MillCert Reader was built for exactly this situation. Here is what the standards actually require, where the manual process breaks down, and how automation fixes it.

What BS EN 1090 Actually Demands From You

BS EN 1090 is the European standard governing the execution of structural steel and aluminium structures. It has two parts that matter for fabricators.

BS EN 1090-1: CE Marking and Factory Production Control

BS EN 1090-1 covers conformity assessment and is the CE marking regime for structural components. To CE-mark a structural steel component, you need to show your FPC system can trace material from incoming steel to finished product.

That means your documentation system must show:

• Which mill produced the source steel
• What EN 10204 certificate covers it
• Which heat number applies to which finished element
• That the declared material properties were verified before fabrication

If you cannot produce that chain of evidence, you do not have a CE mark that means anything. And without a CE mark, you cannot legally place structural components on the UK market.

BS EN 1090-2: Technical Requirements and Execution Classes

BS EN 1090-2 specifies the technical requirements for steel structure execution, including material requirements by execution class. The classes run from EXC1 (simple structures, low consequence of failure) through to EXC4 (structures with extreme consequences of failure such as major bridges, nuclear facilities).

For execution classes EXC2, EXC3, and EXC4 which cover the vast majority of commercial and public building projects the standard requires:

• EN 10204 Type 3.1 certificates for all structural steel (and Type 3.2 for EXC4 or where the contract specifies)
• A documented system for identifying and tracing material from receipt through to the final structure
• Records of incoming inspection, including verification that received material matches the stated certificate
• Traceability marking maintained on steel elements throughout fabrication

The 3.1 and 3.2 distinction matters. A Type 2.2 test report — the kind that comes with commodity steel without any mill reference to a specific order is not sufficient for EXC2 and above. You need a 3.1 certificate which is issued by the mill’s own testing representative, referencing the specific heat number of the material you received.

Getting that documentation is one problem. Proving you have it and that the values on it are what they say they are is another.

NSSS Piles On — Here Is What Else You Need

The National Structural Steelwork Specification (NSSS) is published jointly by the BCSA and the Steel Construction Institute. It shows up in almost every structural steelwork contract in the UK.

The NSSS does not replace BS EN 1090-2 it works alongside it, adding UK-specific requirements for building projects. It requires:

• Mill test certificates (to EN 10204) for all structural steel, submitted to the client or their representative before or alongside delivery
• Traceability of material from the mill certificate to the fabricated element, maintained through marking, records, or both
• Records retained for the duration of the project and a period after practical completion. This is often ten years minimum under construction contract terms.

That last point is the one that bites fabricators. You are not just managing certificates for the duration of a job. You are maintaining a document library that needs to remain searchable, auditable, and provably complete for a decade. Folders of PDFs with no metadata are not going to cut it when a building owner asks for the traceability records on an element in ten years’ time.

Here Is Where the Manual Process Falls Apart

Here is what happens in most fabrication shops today.

Steel arrives with a certificate. Someone files it in a folder named by job or heat number. The element gets marked with a heat number or piece mark. When the time comes to compile documentation for the client, someone manually matches the element marks to the certificates. They scan the PDFs. They email them across. If the client queries a yield strength value, someone pulls the certificate and checks it manually against the spec. Every time. For every query.

This works, after a fashion. It worked in 2005. It barely works now. Until the folder structure breaks down. Until someone files the cert under the wrong job. Until the certificate for heat A321 gets confused with the certificate for A231. Until a client asks for every cert for elements from a specific mill. And there is no way to answer that without opening every single file.

Frequently Asked Questions

Stop Guessing, Start Knowing

BS EN 1090 and NSSS do not ask for a best-effort filing system. They ask for demonstrable traceability and a verifiable audit trail. The manual approach gets close enough until it does not which is usually at the worst possible moment, when a project is complete and someone is questioning the documentation.

GoSmarter turns mill certificate management from a compliance risk into a compliance asset. The data is there. The audit trail is there. The validation records are there. When the question comes, you have the answer.

Upload your first cert — it takes ten seconds →

Or see what GoSmarter does with your actual certificates — bring one along to the call.

Go Deeper

• Mill Certificate Automation for Metals Manufacturers — the complete guide to what GoSmarter does with mill certs
• GoSmarter MillCert Reader product page — features, pricing, and free trial
• GoSmarter vs Generic OCR/IDP Tools for Mill Certificates — why metals-specific AI wins
• Mill Test Certificate Management: Common Questions Answered — EN 10204 explained

GoSmarter is made by Nightingale HQ, a UK-based AI company building practical tools for metals manufacturers since 2018.

Here’s the truth: Outdated systems are costing you far more than you realise. Whether it’s chasing data across clunky spreadsheets or losing 60% of raw material costs to scrap, the old ways are holding you back. AI tools like GoSmarter can fix this mess - cutting scrap rates, slashing energy costs, and preventing downtime.

The Old Way vs. The Smart Way

The result? Better margins, fewer headaches, and a business that runs like it should. Let’s break down how AI can transform your operations.

Reduce Scrap and Material Costs with AI

Scrap isn’t just wasted material; it’s a direct hit to your bottom line. Did you know you only recover about 40% of raw material costs from scrap? That means 60% is pure loss. While the industry aims for a scrap rate of 2.5%, many UK manufacturers find themselves stuck between 3% and 8%. Every percentage point above the target eats into profits, turning production into a costly exercise. This is where AI steps in, transforming waste management into a profit-saving strategy.

GoSmarter’s Rebar Optimiser uses genetic algorithms to tackle the 1D Cutting Stock Problem. It evaluates thousands of cutting combinations across multiple orders to find the most efficient sequences [4][5]. Unlike manual methods that focus on one order at a time, AI looks at the bigger picture, matching offcuts from one job to another to reduce waste [5]. The Offcut Tracker App takes this a step further, monitoring leftover pieces and reassigning them to future jobs, ensuring nothing usable goes to waste [4].

Manual Scrap Tracking vs. AI Optimisation

Traditional scrap tracking methods rely on spreadsheets and static rules, which struggle to keep up with the fast-paced demands of modern manufacturing. AI, on the other hand, integrates real-time data from inventory, job schedules, and even sustainability metrics like carbon equivalence. This allows manufacturers to achieve efficiency rates of 92–98% of the theoretical maximum, compared to the 60–70% ceiling of manual methods [2].

How UK Manufacturers Cut Scrap by 50%

Elsewhere in the industry, Ryobi Aluminium Casting in Carrickfergus, Northern Ireland, shows what’s possible. By implementing AI-driven predictive modelling, they slashed their scrap rate from 6% to just 1.5% by February 2026 - a 75% reduction. Beyond cutting scrap, they improved defect detection accuracy to 96% and reduced inspection times from 10 seconds to just 2 seconds. For every tonne of scrap avoided, they prevented 1.9 tonnes of CO₂ emissions.

These results show how AI doesn’t just reduce waste - it strengthens margins and boosts production efficiency.

“Smart technology can directly contribute to reducing carbon emissions in steel manufacturing. By integrating AI and digital tracking tools, we have significantly improved efficiency whilst aligning with our sustainability goals.” [4]

• Tony Woods, Managing Director, Midland Steel

Lower Energy Costs with AI Controls

AI doesn’t just kill scrap waste. Your energy bill is next. With energy making up 20–40% of production costs, every wasted kilowatt eats into your margins [8][9]. Traditional manual furnace controls depend on operator intuition and often err on the side of over-heating to avoid quality issues. This approach burns through energy unnecessarily. AI, on the other hand, uses real-time data from hundreds of sensors to calculate the exact thermal distribution inside each slab. It adjusts setpoints every 30 to 60 seconds, taking the guesswork out of the equation [6][8].

AI-driven furnace optimisation delivers:

• 5–12% reduction in specific energy consumption
• 50–70% improvement in temperature uniformity
• 3,000–10,000 fewer tonnes of CO₂ per furnace, per year [6]

One major steel producer saved £14 million a year in energy costs and slashed utility demand charges by 40 MW per month after implementing AI in its hot roll mill [11]. These aren’t just small wins. They’re the kind of change that shows up in your accounts within months.

AI-Controlled Furnace Temperatures

Traditional furnace controls often overheat zones to avoid rejects, and manual adjustments during mill stops waste even more energy [6]. AI flips this approach on its head. Using advanced modelling, it calculates the lowest possible temperature needed to meet metallurgical requirements. It then adjusts fuel and oxygen inputs in real time, guided by data like exhaust gas composition, slab tracking, and zone temperatures [6][8].

In Electric Arc Furnaces, AI optimises the balance between electrical and chemical energy inputs - like oxygen, carbon, and burners - based on real-time scrap composition. This reduces specific energy use by around 37 kWh per tonne [7]. When the mill stops, AI cuts fuel within 30 to 60 seconds, avoiding unnecessary energy loss [6]. It also tightens temperature uniformity, reducing variation from ±22–33°C to just ±7–11°C. Every 28°C drop in peak zone temperature cuts oxide scale formation by about 15%, reducing material loss [6]. These improvements don’t just save energy - they also reduce peak demand costs significantly.

“The AI isn’t replacing operators - it’s giving them a tool that handles the optimisation maths they were never equipped to do manually.” [6]

• John Mark, Author/Expert, OxMaint

Calculate Your Energy Savings

Start by monitoring power usage at 15-minute intervals over three months and ensure sensors are properly calibrated. This will help identify inefficiencies and reduce peak demand charges by up to 25% [7][9]. Measure energy use in GJ per tonne or kWh per tonne by grade - aggregate figures often hide where the real losses occur [6]. AI systems can highlight energy variances of up to 340 kWh per tonne between shifts, exposing inefficiencies you might not even realise exist [10].

Peak demand charges can make up 30% to 50% of your electricity bill, and AI can shave off 25% of these costs by intelligently shifting loads [7][9]. Most AI systems pay for themselves within 4 to 8 months [6]. To ease the transition, run the system in advisory mode for 6 to 8 weeks to build operator confidence before moving to full automation [6]. The maths is simple: every 1% drop in specific fuel consumption cuts CO₂ emissions by 1% [6]. The result? Lower bills, better margins, and cleaner operations.

Prevent Downtime with Predictive Maintenance

Unplanned downtime doesn’t just disrupt production - it eats into profits. For steel plants, the cost of equipment failures can skyrocket to £11,500 per minute [13]. While traditional reactive maintenance waits for things to break, and time-based preventive schedules can either replace parts too soon or miss impending failures, AI predictive maintenance offers a smarter solution. It predicts failures days or even weeks in advance, allowing repairs to be planned during scheduled downtime.

Downtime costs 1.6× more than it did in 2019. The meter is running [13]. AI predictive maintenance puts a stop to it:

• Unplanned downtime: down 30–50%
• Equipment lifespan: up 20–40%
• Maintenance costs: down 10–40% [23–27]

95% of manufacturers using AI see a positive return on investment, with the system often paying for itself within a year [13].

How AI Detects Equipment Problems Early

AI watches the metrics your team doesn’t have time to watch: vibration, temperature, pressure, acoustic signatures. It flags subtle issues long before your next scheduled check [24,26,27]. It also calculates the Remaining Useful Life (RUL) of parts — so you know exactly when to act [18,23,27].

Elsewhere in the industry, Sasol shows the same principle in action. Their engineers used MATLAB to analyse six years of turbine data, focusing on wheel chamber pressure and speed. They built a predictive model to forecast salt deposit fouling, optimise wash schedules, and gauge the turbines’ remaining lifespan. This approach helped them avoid unexpected shutdowns [12]. Similarly, AI can spot bearing failures over 10 days in advance and refractory issues 2–4 weeks ahead [13], giving teams plenty of time to order parts and schedule repairs.

Catch the problem early. Fix it on your schedule. That’s how you drag a legacy plant into 2026 without tearing the floor apart.

Add AI to Your Existing Systems

You don’t need to tear down your current setup to adopt predictive maintenance. Non-invasive IoT sensors - designed to monitor vibration, heat, and sound - can be added to existing equipment without disrupting operations [20,22]. These sensors feed data into AI platforms that talk directly to your ERP, PLC, SCADA, or CMMS via standard protocols [13]. GoSmarter’s Legacy Integration feature, for instance, works with what you already have, so there’s no need for a complete overhaul.

Start small with a pilot project targeting your “Critical 10–15” assets - the machines where failures would cause the most chaos. Allow the AI to observe and learn normal operating patterns over 4–6 weeks before rolling it out fully [20,21]. At BMW’s Regensburg plant, for example, an AI system monitored conveyor power consumption, identifying movement irregularities that helped prevent roughly 500 minutes of production downtime annually [15].

And the cost? Surprisingly manageable. For a steel plant, initial investment typically ranges from £65,000 to £140,000, with yearly maintenance costing less than £15,000 [13]. Smaller operations, like mini-mills or specialty producers, could get started for under £40,000 [13]. This upgrade turns your equipment into self-diagnosing assets, keeping production on track and profits growing [14].

Deploy GoSmarter and Improve Margins Immediately

AI cuts scrap by half, slashes energy bills, and stops expensive downtime. GoSmarter puts that to work in your operation. You’re up and running in days, not months — no IT department needed, no drawn-out six-month implementation process [1].

Get Started in Days, Not Months

Forget lengthy ERP overhauls and consultancy delays. GoSmarter bolts onto your existing systems — AI, OCR, and automation, all wired in without a six-month IT project. You’ll be operational within days [1][2][16].

The MillCert Reader AI eliminates manual data entry from mill certificates immediately, while Business Manager swaps out clunky spreadsheets for streamlined inventory and production tools tailored to the shop floor [1]. You can run the Business Case Calculator for free before you spend a penny. Paid plans include a trial period so you see the impact before you commit [1].

Once you’re live, the benefits start rolling in, with measurable ROI to prove it.

Track Your ROI in Weeks

GoSmarter’s Business Case Calculator shows you exactly where your savings are coming from [16][17]:

• Scrap rates — down, thanks to smarter cutting plans
• Energy bills — lower, from AI-controlled furnace settings
• Breakdown costs — gone, because problems get caught before they happen

These results aren’t hypothetical. You’ll see measurable gains in just weeks.

Build Stronger Margins for the Long Term

Fast setup. Clear ROI. Your margins stop bleeding and start growing. As Tadhg Hurley, Managing Director at MAAS Precision Engineering, puts it:

“We’re constantly seeking ways to improve our systems and processes with technology, and this has been a great opportunity to accelerate our adoption of smarter tools that open up new opportunities” [1].

Stop firefighting. Start winning back the margin you’ve been handing to the scrap merchant for years.

Frequently Asked Questions

You’ve got a smartphone in your pocket that can map the stars. But back at the office? A skilled engineer — someone you pay six figures to solve complex metallurgical problems — is spending six hours a day copy-pasting data from PDFs. The destination? A green-screen terminal that belongs in a museum.

That’s not “process management.” That’s insanity. At GoSmarter, we’re here to break that cycle. It’s time to talk about AI for metals without the corporate buzzwords, the fleece vests, or the “synergy” crap.

The State of Metals Manufacturing AI (And Why Most of It Sucks)

If you read the reports from the big-name consultants, they’ll tell you that metals manufacturing AI is a “paradigm shift” for “holistic value chain optimisation.”

Translate that from “Boardroom” to “Bar Stool,” and it means: your factory is currently leaking cash because you’re relying on 1990s tech to solve 2026 problems.

The industry is waking up, though. Research on the AI-powered mining and metals company suggests that the winners of the next decade are already focusing on radical productivity gains. McKinsey’s OptimusAI shows how engineers are squeezing every last drop of efficiency out of their production lines.

But here’s the problem: most of these tools are built by tech bros who have never stepped foot in a foundry. They want you to “rip and replace” everything you’ve built over the last twenty years. They don’t respect the metal; they only respect the code.

At GoSmarter, we take a different approach. We don’t ask you to kill your “dinosaur” legacy systems; we just make them act their age. We aren’t here to replace your expertise; we’re here to give you your brain back.

The Real Benefits of AI in Metals

So, what are the actual benefits of AI in metals? It isn’t about having a robot do your job. It’s about stopping the manual drudgery that is killing your margins and your morale.

1. Stopping the Paperwork Nightmare

The average metals firm is drowning in a sea of mill certs, spreadsheets, and shipping manifests. If you don’t laugh at a pile of 500 unread certificates, you’ll cry.

Industry leaders like the SMS Group are already vocal about how AI is transforming the industry by turning this data chaos into actionable insights. At GoSmarter, we help firms process certificates 60% faster. That’s 60% less time your team spends doing data entry — which, let’s be clear, shouldn’t be a job description for an engineer anyway.

2. Slashing Scrap and Waste

Sustainability isn’t just a PR move for the annual report; it’s about margins. Experts in artificial intelligence in the sheet metal industry point out that AI is the key to optimising nesting and reducing material waste.

We’ve seen the “receipts” firsthand: one of our partners, Midland Steel, cut their scrap by 50% using our tech. That’s not a typo. When you apply metals manufacturing AI to the shop floor, you stop burning cash and start hitting your targets.

3. Hedging Against the “Silver Tsunami”

Your most experienced guys are retiring. The new hires? They don’t want to use a system that requires a 400-page manual and a dial-up modem. As Bronk & Company notes, the question is no longer “if” AI will be integrated, but “where” it is today.

If your tools look like they belong in 1985, don’t be surprised when your best talent leaves for a shop that actually lives in the 21st century. AI allows you to institutionalise the knowledge of your veterans so it doesn’t walk out the door when they do.

Why GoSmarter is the “No-BS” Challenger

We know what you’re thinking: “Another software implementation? I’d rather have a root canal.”

We get it. “Implementation hell” is a real place, and it’s usually paved with “gold-plated” ERP upgrades that never actually work. That’s why GoSmarter is built for AI for metals with a “Zero-Config” philosophy. If you can use Facebook, you can use GoSmarter.

We don’t “leverage synergies.” We fix the mess.

• We speak your language: We’re the smartest engineer on the shop floor who isn’t afraid to tell the boss the new software is garbage.
• We play nice with your “dinosaur” tech: You don’t need to scrap your existing ERP. We act as the intelligent layer that actually makes sense of the data.
• We focus on the ROI that matters: You wouldn’t worry about the price of a pint if your margins were better. Our goal is to take a sledgehammer to the bottlenecks that are killing your profitability.

The Silent Revolution

Here’s the quiet truth: while some factories are still printing PDFs and arguing about who left the spreadsheet open, others are already automating the dull stuff. The shift is happening. The question is whether you’re in the first group or the second.

Revenue.ai, MHI, and the World Economic Forum are all saying the same thing in different ways. The factories that survive the next decade won’t be the ones with the best legacy ERP. They’ll be the ones who stopped letting 2005-era software make 2026-era decisions.

Metals-AI puts it plainly: the future of the industry depends on this technical pivot. We earn our credibility the old-fashioned way: our tech actually works.

(And a quick side note: if you’re searching for this tech, make sure you’re looking for industrial solutions. We’re great, but we aren’t the Metal AI that generates music — though we do appreciate a heavy beat while we’re crushing data.)

Stop the Insanity

The “old way” of running a factory is drowning in paperwork and hoping for the best. The “new way” is using metals manufacturing AI to actually see what’s happening on your floor in real time.

The benefits of AI in metals are clear: higher margins, happier engineers, and a business that isn’t held hostage by a 30-year-old database.

Your competitors are already looking for ways to automate the boring stuff. You can keep paying people to copy-paste from PDFs until the cows come home, or you can cut the BS and see how much time you’re actually wasting.

Ready to get your brain back? Stop the insanity and see how GoSmarter.ai works.