Provides a bounded read order, current-state summary, open questions, next actions, checks, and blockers for the next maintainer or AI agent.
Read order
- AGENTS.md and .uai/readme.human.
- Memory maintenance and active instruction anchors.
- Identity, world context, and short-term memory.
- Startup packet, system profile, receiver brief, context, and constraints.
- Architecture, coding standards, tests, progress, decisions, risks, and next actions.
- Active Content and Improvement buckets.
First report
State the selected project root, active intake status, current versions, project boundary, intended change, checks, and blockers before broad edits.
Scope
This starter page defines the questions, boundaries, evidence, and failure modes that should be recorded before a capability is presented as supported.
Engineering considerations
- Identify the source, version, target environment, and owner.
- Separate observed values from estimates and externally reported values.
- Record trade-offs, unsupported cases, and fallback behavior.
- Link performance statements to a compatible benchmark methodology.
Verification questions
- What exact artifact, revision, backend, and environment were reviewed?
- Which assumptions could change the result?
- Which data should be retained so another engineer can reproduce the conclusion?