Write an operator handoff for stale or unavailable assistance
Operators must continue handling incidents when the assistant is down.
- Focused work estimate
- 1h + prerequisites
- Priority in the scenario
- Low
- Engineering practice
- Runbooks
Estimated field mix
- Site reliability60%
- Applied AI40%
Field percentages are editorial estimates of the ticket's engineering focus. They total 100%; they are not measured time, proficiency scores, or ownership evidence.
Review it, then add it to your workspace.
The board opens an editable draft; nothing is saved until you confirm it. Sign-in and workspace permissions apply, and Demo boards remain ephemeral.
Project context
A fictional on-call team wants an assistant that joins alerts, deployment notes, and runbooks. Incomplete telemetry and hostile log content make unsupported conclusions dangerous.
Setup prerequisites
- Author synthetic alerts, deployment records, and runbooks plus deterministic tool and model doubles.
Preceding work
Complete these dependencies, or supply their agreed outputs before taking this ticket.
- BTRIAGE-101 · Define a common timeline record for operational events
- BTRIAGE-102 · Limit incident retrieval to the caller's service grants
- BTRIAGE-103 · Bound tool arguments and returned telemetry volume
- BTRIAGE-104 · Keep log content from issuing new tool instructions
- BTRIAGE-105 · Require source references for incident summary statements
- BTRIAGE-106 · Represent competing incident hypotheses explicitly
- BTRIAGE-107 · Cancel obsolete drafts when new incident context arrives
- BTRIAGE-108 · Prevent repeated refreshes from exhausting incident budgets
- BTRIAGE-109 · Evaluate summary utility without rewarding confident guesses
Acceptance criteria
- Show draft age and source window.
- Link the original authorized records.
- Document the manual timeline workflow.
Implementation constraints
- The assistant is never a dependency for incident response.
Verification to include
- Continue from source records during provider failure.
- Verify stale drafts cannot appear current.
Deliverables
- Operator fallback guide.
Rollout and recovery
Ship the fallback with the prototype and rehearse it locally.
Value of the work
For the engineer: Practice constrained tool use, operational uncertainty, and traceable AI outputs.
For the team: Produce concise incident drafts that preserve source traceability and operator control.
Evidence boundaries
Outcome Evidence: Tests, patches, and runbooks are requested deliverables. They become Outcome Evidence only through a qualified Mission and immutable Evidence IDs.
Ownership Evidence: Independent adaptation must be observed under a declared verification policy and cite immutable Evidence IDs. Completing a planning ticket establishes no Ownership Evidence.