In plain English
This page is reference material: definitions, schemas, catalogs, templates, and implementation records.
- Why this matters: AI risk can come from the whole arrangement, not one obvious model.
- What to look for: data, memory, routes, adapters, tools, evaluators, updates, and rollback paths.
- Technical version below: the expert terminology remains available and is linked through the glossary.
Incident Review Template
Summary
Record the incident in UTC, affected users, affected components, and immediate containment status.
Composition
Attach the exact composition manifestA machine-readable record of the exact runtime composition used for an evaluation, release, incident, or rollback. Open glossary definition and release alias state.
Timeline
List route changes, memory changes, evaluatorA system that judges whether an AI output or candidate is acceptable. Open glossary definition changes, permission changes, and release events in UTC.
Behavioral persistence review
Identify whether behavior remains expressible through descendants, memory, synthetic data, routes, adapters, or evaluator preferences.
Recovery
Attach ecological rollbackRestoring not only a model artifact but the relevant router, prompts, memory state, tool permissions, evaluator version, deployment alias, and data dependencies. Open glossary definition packet, side-effect remediation, owner assignments, and follow-up evidence.