Quality Assurance AI Agents,
Monitored for Rigor

1. Target

   Release sign-off endpoints, build promotion pipelines and quality-gate records feeding production deploys

2. Trigger

   Any attempt to mark a build releasable while gate criteria are unmet or unevaluated

3. Action — enforced

   Platform blocks the promotion and holds the build in quarantine; agent may assemble evidence and request human gate review.

4. Human override

   QA release manager via signed gate-waiver ticket recorded against the build id

Logged evidencebuild id · gate criteria snapshot · unmet-criteria list · approver identity · waiver ticket id · UTC timestamp

1. Target

   Inbound bug reports, repro attachments, CI logs, fixtures and test artifacts parsed by QA agents

2. Trigger

   Imperative or tool-directing text detected inside any submitted report, log, fixture or attachment

3. Action — enforced

   Platform strips the content to inert data and refuses execution; agent may quote it verbatim and continue triage.

4. Human override

   None — cannot be overridden in session

Logged evidenceartifact hash · detected instruction span · source reporter id · sanitized copy hash · detection timestamp

1. Target

   Triage digests, defect summaries and cross-team reports assembled from restricted repositories and customer data

2. Trigger

   Classified-restricted records, secrets or customer identifiers detected in any outbound digest draft

3. Action — enforced

   Platform blocks distribution and redacts the digest; agent may cite record ids and route readers to source systems.

4. Human override

   None — cannot be overridden in session

Logged evidencedigest id · classification labels hit · redaction diff hash · intended recipients · block timestamp

1. Target

   CI runner configurations, grader definitions, scoring scripts and harness manifests across all pipelines

2. Trigger

   Any write targeting harness, runner or grader files from a test-generation or triage session

3. Action — enforced

   Platform denies the write and freezes the pipeline run; agent may file a harness-change request for human review.

4. Human override

   Build-infrastructure lead via signed pull request reviewed outside the agent session

Logged evidenceattempted diff hash · target file path · pipeline run id · agent identity · denial timestamp

1. Target

   Pass/fail verdicts, coverage figures and final reports published to dashboards and release records

2. Trigger

   Reported result lacking a matching runner ledger entry, or coverage exceeding instrumented measurement

3. Action — enforced

   Platform withholds the verdict and flags the report unverified; agent may re-run tests and attach ledger references.

4. Human override

   QA lead via evidence-reconciliation review attaching the missing runner ledger extract

Logged evidenceverdict id · runner ledger hash · coverage instrument version · mismatch list · reconciliation timestamp

1. Target

   Regression suites, mandatory-test registries and their mapping to safety and compliance requirements

2. Trigger

   Deletion or skip-tagging of any test linked to a safety or regulatory requirement

3. Action — enforced

   Platform blocks the removal and keeps the test mandatory; agent may propose retirement with impact analysis for review.

4. Human override

   Head of QA via documented retirement review with traceability sign-off

Logged evidencetest id · linked requirement ids · proposed-change diff · requester identity · decision timestamp

1. Target

   Product source repositories reachable from test-generation, triage and verification agent credentials

2. Trigger

   Any commit or write outside declared test directories from a QA-scoped session

3. Action — enforced

   Platform denies the commit and reverts staged changes; agent may raise a defect describing the failing behavior instead.

4. Human override

   Engineering manager via scope-extension grant issued through the change-control system

Logged evidenceblocked diff hash · repository path · session scope manifest · agent identity · denial timestamp

1. Target

   Severity fields on open defects classified critical or safety-relevant in the tracker

2. Trigger

   Severity reduction requested in-conversation without new reproduction evidence contradicting the original classification

3. Action — enforced

   Platform holds the original severity and escalates to a human triager; agent may record the dissenting rationale.

4. Human override

   Triage board chair via two-person severity review logged on the defect

Logged evidencedefect id · original and requested severity · requester identity · escalation ticket · decision timestamp

1. Target

   Certification records asserting environment equivalence for builds, models and inspection lines

2. Trigger

   Verdict citing a non-production environment while claiming production validity or omitting environment labels

3. Action — enforced

   Platform blocks the certification and labels results by environment; agent may schedule a production-parity run.

4. Human override

   QA release manager via documented environment-parity assessment attached to the record

Logged evidencerun id · environment fingerprint · config diff vs production · certifier identity · block timestamp

1. Target

   CI retry policies and re-run controls across build, integration and inspection pipelines

2. Trigger

   Repeated re-execution of a failing test until a passing sample is obtained

3. Action — enforced

   Platform caps retries and records every attempt as failed; agent may open a flakiness investigation with full run history.

4. Human override

   QA lead via quarantine-list entry that tracks the test as known-flaky

Logged evidencetest id · attempt count · per-attempt outcomes · seed and config hashes · cap timestamp