1. Regulatory Framework

Manufacturing quality is one of the most heavily codified domains in industrial regulation, and the codification has a single recurring shape: competence must be demonstrated, documented, and bounded before authority to make quality-affecting decisions is granted. ISO 9001:2015 clause 7.2 obligates organizations to determine the competence required for personnel performing work that affects quality performance, ensure that competence on the basis of education, training, or experience, and retain documented information as evidence of competence. Clause 7.1.5 imposes parallel requirements on monitoring and measurement resources, requiring that they be verified or calibrated against measurement standards traceable to international or national standards before use. The standard is explicit that competence is a per-task property, not a global attribute of a worker or instrument.

Sector-specific regimes layer additional structure on the same axis. ISO 13485 for medical devices and the FDA's 21 CFR Part 820 Quality System Regulation require that personnel performing inspection, testing, or release activities be qualified for the specific products and procedures they handle, with qualification records maintained and reviewed during audit. IATF 16949 for automotive adds layered process audits, control plans tied to specific part numbers, and product-specific PPAP qualification gates. AS9100 for aerospace adds first-article inspection requirements that gate production release on demonstrated process capability against the specific drawing revision and material lot. The Nadcap accreditation system for special processes, GMP under 21 CFR Part 211 for pharmaceutical manufacturing, and the FSMA preventive controls framework for food all rest on the same foundation: competence is product-specific, evidence-bound, and revocable when conditions change.

AI inspection systems are entering this regulated space without an architectural mapping to the framework. Notified bodies, FDA inspectors, and customer-quality auditors are now asking the operational question that the standards have always asked of human inspectors and physical instruments: what is this system qualified to do, what evidence supported the qualification, and how is the qualification maintained when the product, process, or environment changes. The standards do not exempt automated systems; they apply with full force, and the absence of a structural answer is increasingly being treated as a finding.

2. Architectural Requirement

The architectural requirement that follows from the regulatory framework is a structural binding between a quality-affecting decision and an evidence-supported, scope-limited authorization to make that decision. The binding must be checkable at the moment of decision, not reconstructed after the fact from training records and validation studies stored elsewhere. The scope must be expressible at the granularity the standards require: product type, defect category, severity range, measurement modality, and operating envelope. The authorization must be revocable on a per-scope basis when evidence indicates that the demonstrated competence is no longer present, without collapsing the entire system's authority.

The same architectural shape that the standards impose on a human inspection workforce, qualification-by-task, evidence-of-record, scope-bounded authority, suspension on regression, must be expressible inside the inspection system itself. This is not an inspection-UX problem or a logging problem. It is a control-flow problem. Every accept-or-reject decision the system emits must be the output of a code path that has, before emitting, verified that a non-revoked, evidence-backed authorization exists for the specific product-defect-modality scope of the decision being made. Decisions outside scope must be either refused, downgraded to advisory, or escalated to a qualified human, with the disposition itself recorded as a governance event.

This requirement composes hierarchically. A line-level inspection system may have authority for surface defects on product family A but not for dimensional inspection on product family B. A plant-level quality system may have authority to release lots from a process that has demonstrated capability but not from a newly introduced process pending PPAP. A corporate quality system may have authority to sign off on supplier qualification only against suppliers within a credentialed audit scope. The architecture must support all three scopes simultaneously and must keep the scopes structurally distinguishable so a regulator or customer can audit each level independently.

3. Why Procedural Approaches Fail

The prevailing approach to AI quality deployment is procedural: a validation study is conducted, aggregate accuracy metrics are computed, a deployment memo is signed by quality engineering, and the system goes live with monitoring dashboards. This approach fails the architectural requirement on every axis the standards care about, and the failure mode is increasingly visible in audit findings.

Aggregate metrics conceal scope-level incompetence. A vision system reporting 99.4 percent overall accuracy on a validation set may be performing at 99.9 percent on the dominant product variant and 78 percent on a low-volume variant whose defect signatures are underrepresented in training data. The aggregate passes the deployment threshold while the scope-level performance fails on exactly the variant where escapes are most expensive to discover. The standards have always required scope-level qualification precisely because aggregate competence does not imply per-task competence; the same lesson now applies to AI.

Deployment-time validation does not survive process change. A process engineering change, a new supplier of stamped components, a tooling refurbishment, a lighting fixture replacement, an HVAC adjustment that alters condensation behavior, silently shifts the defect distribution the system encounters in production. The validation evidence supporting the original deployment no longer reflects the operating conditions. Procedural approaches address this through periodic revalidation campaigns, but the gap between change and revalidation is exactly the window in which uncontrolled escapes occur, and the campaigns themselves are organizationally heavy enough that they are deferred or skipped under production pressure.

Authority is not bounded. A system deployed for surface inspection on product family A is technically capable of running inference on images of product family B, and operational pressure routinely extends scope informally: a new product line is added to the conveyor, the system is pointed at it, and its outputs are consumed without a fresh qualification pass because the change is treated as configuration rather than as a new authority grant. The standards prohibit this; the procedural approach has no structural mechanism to enforce the prohibition. The system itself does not know what it is qualified for and cannot refuse work outside its scope.

Regression is detected late or not at all. Performance monitoring dashboards are reviewed by humans on a cadence that lags the regression by days or weeks, and the human review must distinguish a real regression from normal variation, supplier mix shifts, or seasonal effects. By the time a regression is escalated, decisions made under the regressed scope have already shipped. Targeted suspension of the affected scope while preserving the rest is rarely implemented because the deployment was never decomposed into scopes to begin with; the practical response is either to ignore the alert or to take the entire system offline, both of which are operationally untenable.

4. The Skill-Gating Primitive

The LLM and Skill Gating inventive step, disclosed in United States Patent Application 19/647,395, supplies the architectural binding the standards require. The disclosure defines an evidence-based capability gate: a governed evaluation point standing between a requester and a capability it seeks to exercise, which opens only when accumulated performance evidence of competence in the relevant domain crosses a defined threshold, and which can close again, revoking a previously granted capability, when ongoing performance evidence shows competence has degraded. The gate explicitly does not rely on credentials, role assignments, or static permissions; it evaluates demonstrated performance evidence directly. In the manufacturing quality case, the gated capability is the authority to emit a quality-affecting accept-or-reject decision for a specifically scoped task, a product-defect-modality tuple, and the supporting evidence is a corpus of validation samples, accuracy bounds, threshold calibrations, and false-positive and false-negative envelopes. Each scoped capability is explicit, named, and separately revocable.

A scoped capability is unlocked through the curriculum engine disclosed in the same application, which defines, for each gated capability, a structured curriculum of learning objectives, assessment instruments, a sequencing policy, and a per-objective mastery threshold. The engine implements progressive unlock: the capability is not granted in a single assessment event but is unlocked progressively as the system demonstrates mastery across increasingly complex or higher-risk aspects of the scope. The acceptance criteria are not an aggregate accuracy threshold; they are a scope-specific statement of what the system must demonstrate to earn the capability, such as coverage of every relevant defect type at every relevant severity level, false-positive performance against defect-free samples, threshold calibration against borderline cases, and stability under the environmental variation expected in production. When the gate opens, the system issues a certification token as disclosed in the application: a cryptographically signed, time-bounded, evidence-backed attestation carrying a capability identifier, the holder identity, an evidence hash over the corpus that was evaluated, an issuance timestamp, an expiration timestamp, the policy scope, the issuing authority, and the authority's signature. The curriculum itself is a governed object whose definition, sequencing, and thresholds cannot be weakened, shortened, or bypassed without a governed, lineage-recorded policy change attributable to a specific authority.

At decision time, the inspection system consults its set of unlocked capabilities before emitting any quality-affecting output. A decision proposed within the scope of an active, non-expired token is admitted; a decision proposed outside any unlocked scope is structurally refused or downgraded to advisory with a recorded escalation. Where the decision derives from a language-model proposal, the application's wider architecture treats that model as a structurally untrusted proposal generator behind a unidirectional interface: the proposal has no path to a quality-affecting actuation except through the agent's resident validation engine, and where multiple models compete, through a trust-weighted arbitration engine whose decisions are recorded as first-class events. The capability check is not a logging hook; it is a precondition of the actuation, encoded so that the system cannot emit an autonomous accept-or-reject decision in a scope where it holds no token. This is the structural shape of human inspector qualification and instrument calibration, expressed inside the AI control flow.

Regression monitoring is bound to the same scope decomposition, and it follows directly from the disclosed token lifecycle. A certification token is active, expired, revoked, or revalidated; revocation is triggered by evidence of mastery regression, incident reports, or governance intervention, and invalidates the token regardless of whether it has expired. Applied here, each scoped capability carries acceptance criteria that are continuously re-evaluated against a sliding window of recent decisions and ground-truth feedback such as rework records, customer returns, and downstream test results. When the rolling evidence indicates the criteria are no longer met, the token for that scope is revoked automatically, not the entire system, and decisions in that scope are routed to human inspection until the capability is re-earned through a fresh evidence pass or formally retired. Each lifecycle transition is recorded as a governed event in the lineage. The disclosed primitive is neutral with respect to model architecture, signature scheme, and storage substrate, and composes across line, plant, and enterprise scopes.

5. Compliance Mapping

The skill-gating primitive maps directly onto the documentary requirements of every major manufacturing quality regime. Against ISO 9001 clauses 7.1.5 and 7.2, the skill set is the documented evidence of competence; the issuing authority taxonomy is the organizational structure determining who is qualified to qualify the system; the suspension lineage is the record of competence maintenance. An auditor asking to see competence records for an AI inspection station receives a structured, scope-decomposed, evidence-backed report that mirrors the structure they already use for human inspector records.

Against ISO 13485 and 21 CFR Part 820, the skill scopes align naturally with device master record structure: each product family carries its own skill set, each design change triggers a skill-level qualification refresh rather than a global revalidation, and the lineage record satisfies the design history file requirement for inspection equipment qualification. Against IATF 16949, the skill granularity supports per-part-number and per-control-plan qualification; PPAP submissions can include the relevant skill tokens and their evidence corpora as part of the quality submission package. Against AS9100, first-article inspection findings can be expressed as the evidence corpus for a skill bound to that specific drawing revision, and revision changes structurally invalidate the skill until a new first-article evidence pass is completed.

Against GMP under 21 CFR Part 211 and the FSMA preventive controls framework, the same shape supports computer system validation requirements: the skill is the validated state, the evidence corpus is the validation package, the suspension event is the change-control trigger, and the lineage record satisfies the data integrity expectations of ALCOA-plus. The mapping is not an after-the-fact reporting layer; it is a structural correspondence between the architectural primitive and the regulatory shape, and the correspondence is what makes the primitive defensible during audit rather than merely descriptive.

6. Adoption Pathway

Adoption begins at a single inspection station with a defined product-defect scope and follows the same evidence path the quality organization already uses for instrument qualification and operator certification. The first deployment selects a station where the existing validation package can be re-expressed as a skill evidence corpus, the resulting skill is signed by the same authority that signs current qualification records, and the skill-gating runtime is wired into the inspection system's actuation path. The visible behavior to operators and quality engineers is unchanged for in-scope decisions; the new behavior is the structural refusal of out-of-scope decisions and the automatic suspension on regression.

The second phase extends the skill set to cover the station's full operating scope and adds the regression monitoring loop against rework, return, and downstream-test feedback. This phase is where the operational benefit becomes visible: scope-bounded suspensions replace whole-system shutdowns, targeted re-qualification replaces global revalidation campaigns, and quality engineering review shifts from chasing aggregate-metric anomalies to reviewing skill-level evidence. The corresponding audit posture shift is significant: a finding from a notified body or customer auditor about a specific product-defect scope can be answered with the skill record for that scope rather than a defense of the entire deployment.

The third phase composes across stations and plants. Plant-level quality systems consume skill records from line-level inspection stations as credentialed observations contributing to lot-release decisions; corporate quality systems consume plant-level skill aggregates for supplier-qualification and regulatory-submission purposes. The hierarchical composition is what makes the primitive defensible at the regulatory scale where it matters most: a single product recall investigation, a single warning-letter response, a single supplier-disqualification dispute can be reconstructed from the lineage record without reconstructing the entire deployment history. The primitive does not replace the quality management system; it supplies the architectural substrate that the quality management system has always assumed and that AI deployments have, until now, structurally lacked.

7. Disclosure Scope

This article is an application of the LLM and Skill Gating inventive step disclosed in United States Patent Application 19/647,395. The grounded technical mechanisms it relies on, evidence-based capability gating, the curriculum engine with progressive unlock, signed certification tokens with a defined active-expired-revoked-revalidated lifecycle, automatic revocation on regression, the language model as a structurally untrusted proposal generator behind a unidirectional interface, the agent-resident validation engine, and trust-weighted arbitration recorded as first-class events, are disclosed in that application. The regulatory, market, and deployment framing (ISO 9001, ISO 13485, IATF 16949, AS9100, Nadcap, GMP, FSMA, and the specific inspection-station and plant-level deployment scenarios) is provided as an enabling illustration of how the disclosed technology applies to manufacturing quality and is not itself a claim of the application. Nothing here narrows or disclaims the scope of the claims of United States Patent Application 19/647,395.