Quality assurance AI agent · Inspection capability
Visual Inspection and AOI AI Agent
Treat the model as an instrument: record what it called, under which version, measure agreement class by class, and leave the validation to the process owner whose name goes on it.
A pass or fail call is attribute data, produced by an instrument, not an opinion.
02
No reference artefact exists for an acceptable joint, so agreement is the only truth there is.
Reason
03
Section 820.75 was reserved on 2 February 2026, and the duty moved into ISO 13485 clause 7.5.6.
04
FDA quoted clause 7.6 at Linemaster on 27 May 2026: software used for monitoring and measurement.
05
Computer Software Assurance went final on 24 September 2025 and superseded Section 6 of the GPSV.
Decide
06
Annex III omits quality control; inspection is a quality function, not a safety function.
07
Regulation (EU) 2026/1744 moved machinery to Section B and deferred Annex III to 2 December 2027.
Out
08
No published method joins classifier scoring to measurement-system analysis, and that is the finding.
09
Execute write actions only inside the approval boundaries agreed during implementation.
→Product statement
Assembly, agreement measurement and versioning belong to the agent. The validation, and the name that goes under it, belong to the process owner an investigator later asks for.
Example workflow
One instrument, images to validation
AgentHuman
1Evidence receivedLabelled images, the reference-truth method, the model version, the optics record and the station
2Agreement study assembledThe held-out set, a temporally later slice, the class balance present and who resolved disagreements
3Capability evidence raisedThe confusion matrix, escapes and false calls, read per defect class and never as one figure
4Controls appliedBalance checks, domain-shift checks, version checks and evidence completeness
No human action required
Stages 1 to 4 run unaided, and nothing is validated at any of them — the agent is measuring, and the owner lane opens at the validation gate.
5DecisionSplits at the validation gate
Agreement inside the criteria
Goes to the process owner to validate.
Anything under-sampled
Adds a quality-engineering read first.
Process-owner review
The pack is held with its images, its per-class results and the studies the agent could not run.
Validate · Extend evidence · Send to engineering review
Validated — by the named process owner▼
6Quality-system and model records updatedOnly where write access and records policy allow it
7Outcome evaluatedEscapes found downstream, false calls on the station, owner corrections and what the later review turned up
Corrections
Each correction the owner makes counts in the evaluation.
What should not run autonomously
Human approval stays in control
Outside the boundary — human approval required8 items
Signing the validation of an inspection process.
Dispositioning a part on the strength of a call.
Setting the agreement criteria a study must meet.
Declaring an instrument capable for its intended use.
Automation boundaryAgent acts unaided
✓Record the model version each call was made under.
✓Run the agreement study against an independently set reference.
✓Report escapes and false calls for each defect classification separately.
✓Hold the evidence pack for the named process owner.
Nothing is validated for production except by a named owner, inside the agreed boundaries.
Judging whether a learned classifier is a gauge.
Telling an investigator the record is complete.
Choosing which defect classes the catalogue admits.
Changes to the validation rules or the release gate.
Example output
One capability pack, annotated
This serves a quality team who may have to defend an instrument to an investigator years after it was validated, against a manual that is industry practice rather than law; below is one pack exactly as the agent leaves it.
Capability pack · single instrumentIllustrative example
Instrument
Recorded as
Defect class
Evidence of record
Confidence
Held for
Surface inspection, one station
Agreement measured, not proven
Per class, not overall
Held-out slice, 6 August 2026
Held unvalidated
The process owner, by name
As receivedDrawn from the labelled set, the held-out slice and the optics record, and it claims nothing past them.
What the record holdsLabelled image setHeld-out sliceOptics configuration
Why no validation hereCalling an instrument capable is a judgement the process owner makes.
ActionValidateExtend evidenceSend to engineering review
What the score decidesBelow the configured threshold a pack gets an engineering read before the owner sees it.
Value
Where AI adds value
The same four claims, placed at the point in the workflow where each one applies.
Where the value landsValue 01 – 04
Each callFrom the instrument that made it
03Evidence
Where the evidence is read
Unomedical was cited on 8 January 2026 under 820.75(a) for an inspection test method never validated, against more than five thousand complaints — three weeks before that section ceased to exist.
01Approved path
A model is a gauge
Its own work instruction required that test to “consistently and accurately differentiate between the possible test states”, which is what a gauge is.
02Human review
What was checked, and not found
ISO/IEC TS 4213 scores classifiers and does not touch measurement-system analysis; AIAG MSA-4 is 2010 and predates deep learning; IEEE P2975.2, which would join them, has held an active PAR since 15 February 2023 and is still unpublished. No independent false-call rate was found.
04Build an evidence trail
The image, the call the model made and the inspector who confirmed it stay together.
Integrations
Typical integrations
Five system groups connect to the same agent. Which of them are in scope is decided in discovery.
Inspection stationsAOI · surface · assembly cells Captured images and their calls
Labelled evidenceImage sets · label stores Reference truth, and who set it
Quality system recordseQMS · validation protocol files Validation records and the triggers
Agent
Visual inspection capability
Reads the instrument Assembles the evidence Holds the validation
Model and training registryModel registry · data versions Model versions and the training cuts
A station-level agreement figure can read clean while unseen defect classes carry most of the owner corrections. Nestack reports the correction rate per defect class, and not only in total.
Slice performance — reported separately, not only in aggregateIllustrative example
Slice
Failure rate
Lift
Lift vs. threshold
Status
Unseen defect classes
8.5%
3.7×
Review
Changed lighting or optics
6.0%
2.6×
Review
New supplier material
3.7%
1.6×
Watch
Catalogued defect classes
1.8%
0.8×
Normal
Bar: correction-rate lift vs. catalogued-class baseline · scale 0–4.0× · tick marks the 2.0× review threshold2 of 4 slices over threshold
Evidence-linked improvement
What an unmeasured class costs
A cycle shuts when the defect class nobody ever labelled is a standing case. That suite is what the next validation run is measured against.
Improvement cycle · five stagesSwitchback — the path turns at Improve and returns at Learn
01Detect
Correction rate rises on unseen defect classes.
02Diagnose
The instrument that passed parts for a month because a lamp had aged, and read confident throughout, is worked backwards until one cause is left standing.
03Improve
Runs ship numbered, and the images behind them travel attached.
04Verify
Each touched agreement case is run again, and one red holds it back.
05Learn
The case is kept, and the validation rules change in that same commit.
Learn → DetectThe return edge. The next validation run meets a suite one case longer.
Typical build scope
Twelve workstreams across six weeks
The build scope read against the delivery timeline. Week structure follows the six-week plan — discovery, sources, evidence assembly, evaluation, integration, then production validation and handover.
WorkstreamWeek 1Week 2Week 3Week 4Week 5Week 6
01Model-as-instrument and automation-boundary scoping.
02Image, label and model-version sources.
03Clause-to-evidence and revalidation-trigger mapping.
04Image and label intake.
05Class binding and pack logic.
06Agreement scoring and review routing.
07Process-owner validation workflow.
08Quality-system integration.
09Agreement and drift cases.
10Guardrails and disposition controls.
11Call-trail instrumentation.
12Deployment, documentation and Agent Care handover.
12 workstreams · 6 weeks · bar shows the weeks a workstream is active — several run in parallelFinal scope and sequence confirmed in discovery
Engagement tiers
What each tier includes
Rows are the capabilities named in each tier's scope. Higher tiers include everything below them.
Capability✓ in scope · — not at this tierPilotOne defect class, one cycleProductionProduction inspection workflowAdvancedMultiple stations / lines
Introduced at Pilot
Evidence assembly to your criteria✓✓✓
Named process-owner validation✓✓✓
Defect-catalogue baseline✓✓✓
Introduced at Production
Reporting by inspection class—✓✓
Engineering review workflow in your systems—✓✓
Approved quality-record write-back—✓✓
Camera-and-line integration—✓✓
Introduced at Advanced
Multi-regime validation rules——✓
Cross-station evidence packs——✓
High image volume——✓
Multi-line validation controls——✓
Build priceFrom $5,000From $8,000Custom quote
Final build priceConfirmed after discovery based on integrations, workflow complexity, image volume, validation controls and deployment requirements.
Separate from buildBuild pricing is separate from recurring Agent Care, which covers managed monitoring, evaluations, incidents and verified improvements after launch.
What we need from you
What you bring, and what we build with it
Each input maps to a piece of build scope and a week in the delivery timeline.
You bringWe build with it
01Your live stations and the defect classes each one calls→Criteria capture and model versioningWeek 1
02Representative images, labels and past validation records→Class binding, pack logic and the defect-catalogue baselineWeek 2
03Your change-control path and the process owner it names→Criteria mapping, class binding and the automation boundaryWeek 1
04Access to relevant APIs, feeds or exports→Station, label and quality-record source assessment, then integration setupWeek 2
05Calls you would not want re-read→Agreement cases and the evaluation roundWeek 4
06What no call may establish→Agreement scoring, review routing, guardrails and release controlsWeek 3
07A named process owner who validates the instrument→Handover to the process owner, then pilot and production validationWeeks 5–6
Nothing else is requiredDeployment, documentation and Agent Care handover are ours.
Delivery timeline
Four phases across six weeks
A band is exactly as wide as its phase costs here, so week five shows a pair where one would look neater.
PhaseW1W2W3W4W5W6
DiscoveryW1
BuildW2 – W3
EvaluateW4 – W5
Pilot & LaunchW5 – W6
Week focusW1Criteria discovery, model versioning and the automation boundaryW2Station and label integration and the defect-catalogue baselineW3Class binding, pack logic and release controlsW4Evaluation suite, agreement cases and failure-mode testingW5Quality-system integration, pilot packs and targeted correctionsW6One validation cycle run under the process owner, then Agent Care handover
Reading the bandWeek five is the only place two bars sit together, and no bar is stretched to fill a row.
At the end of W6When the validation record validates, Agent Care picks the agent up.
DurationSix-week plan shown · typical delivery 4–6 weeks depending on scope confirmed in discovery.
Next step · Quality assurance AI agent
Build a visual inspection agent around the validation your last model was never given.
Show us one inspection a model already decides and the record behind it. Not how it scored on a benchmark. Which defect classes sat in the labelled set, who set the reference truth, and whose name is on the validation. A class nobody labelled comes back as a case.
