Happy Webs
№ 01 / SolutionQC inspection · Fabricators

Catch the Defect Before It Leaves the Bay.

In fabrication, the cost of a missed defect on dispatch is the customer rejection email, the haulage cost both ways, the rework slot you didn't plan for, and the relationship damage. AI vision inspection runs on the photos your team already takes — and catches what gets missed when the QC inspector is on their 200th part of the day.

№ 02The promise

The promise

< 2 sec inspection time per part
£0 extra hardware in most deployments
24/7 consistent — no afternoon-fatigue defects
№ 03Where it hurts

Where it hurts

The fabricators reality.

Your QC inspector is good at this. They're also human. After 200 parts on a Friday afternoon, attention drifts. Missing fillet welds, wrong finishes, off-spec dimensions, missing tags — these are the defects that should never leave the building. Customers expect photo evidence anyway, so the inputs already exist on someone's phone. The question is whether you're using them as inspection or just archive.

№ 04What we actually build

What we actually build

Tuned for fabricators.

01

Define "right" per part type

For each common product type (gates, frames, balconies, brackets, etc.) we agree the inspection checklist — welds present, finish correct, dimensions within tolerance, packaging right, tags attached. Structured as machine-checkable schema.

02

Use the photos you already take

Pre-dispatch phone photos, fixed-camera shots at the QC bay, customer-spec photo packages. Same model handles all sources. No specialist hardware needed in most cases.

03

Inspect against the schema

For each photo: pass/fail per criterion, with reasoning. Missing weld? Flagged. Wrong colour? Flagged. Damaged corner? Flagged. Tags not attached? Flagged. Clean parts go through to dispatch with a confidence score.

04

Audit trail for customers and ISO

Every inspection logged with the input image, schema applied, decision, and reasoning. ISO 9001 audit trail without paper. Customer queries six months later: pull up the dispatch photos and the AI inspection record.

№ 05Real engagement

Real engagement

The outcome.

Kingsland Fabrications

AI-driven QC inspection on fabricated parts pre-dispatch. Catches defects (missing welds, surface issues, wrong configurations) before they ship — including the cases human reviewers were previously missing on busy days.

№ 06Typical stack

Typical stack

We integrate with what you have.

  • Phone cameras / shop tablets
  • Custom MES
  • Microsoft 365 / Google Workspace
  • Customer-specific photo packs
  • ISO 9001 / 14001 audit logs

If your stack isn't listed, ask — almost always we can integrate. We've connected to bespoke MES, ancient on-prem systems, and email-only interfaces.

№ 07Pricing

Pricing

Fixed fee, phased delivery.

£3,200–£10,000 for build, ~£150–£400/month for hosting + accuracy monitoring

From £3,200

QC inspection for fabricators

  • Workflow audit + industry-specific spec
  • Build, integrations, and tuning to your real data
  • Live deployment in your environment
  • Ongoing tuning + accuracy monitoring
№ 08Questions

Questions

Things people in this industry ask us.

01 Will it replace our QC inspector?

No — it changes their job. They go from looking at every part to reviewing flagged cases, tuning the system, and handling complex inspections. Most clients keep the same headcount and take on more dispatch volume.

02 Is this auditable for ISO 9001?

Yes — every decision is logged with input image, the inspection schema applied, the confidence scores, and the outcome. That's a cleaner audit trail than a paper log signed by a person who looked at 200 parts that day.

03 What about parts that need physical measurement?

AI vision can't replace callipers or CMM checks. But it can flag "this looks visually wrong, take a measurement" — which is usually the trigger that's missing. We pair vision with manual measurement workflows where appropriate.

04 How do you train it on our products?

A handful of reference photos per product type — typically 10-30 — and a written checklist. We tune over the first month based on flagged cases and overrides. Adding new product types is straightforward.

05 Where do the photos and decisions live?

In your environment. We can run fully on-premise if that's a requirement. Models we use don't train on your data — we sign DPAs and use zero-retention API contracts.

Let's see if we can help.

A 15-minute chat with Chris & Kay. No slides. No pitch deck. You tell us what's on your plate; we follow up by email with real thinking.

Studio81 Penny Meadow, Ashton-under-Lyne, OL6 6EL
HoursMon–Fri · 09:00–17:00 GMT