Evidence the run may read
- Current runbook
- Service configuration snapshot
- Recent incident lessons
production blueprint · engineering
Technical runbook refresh agent blueprint.
Compare a runbook with current service evidence and propose precise updates for an owner to approve.
Search intent: AI agent for runbook maintenance
Published by a2a cloudProduct-source methodology →
01 · the contract
Start from a bounded job, not a blank chat box.
trigger
A service changes or a runbook reaches its review date.
owner
engineering owner
agent stops at
The service owner approves and publishes the runbook change.
KPI · increase
runbook validation success (percent). Measure scheduled drills completed using the approved runbook without undocumented steps.
outputs
Artifacts the run must produce
- Staleness report
- Proposed runbook patch
- Validation checklist
02 · topology
Small specialists. Named handoffs. One accountable decision.
Each stage produces an artifact another stage can inspect. The final node is a person, not an autonomous write to an external system.
- 01
intake
Validate and normalize the technical runbook refresh inputs.
- 02
runbook auditor
Produce the staleness report.
- 03
service-state mapper
Produce the proposed runbook patch.
- 04
operations reviewer
Challenge the technical runbook refresh result and prepare an approval packet.
- 05
engineering owner
The service owner approves and publishes the runbook change.
intake→ validated input packet →runbook-auditor
runbook-auditor→ Staleness report →service-state-mapper
service-state-mapper→ Proposed runbook patch →operations-reviewer
operations-reviewer→ approval packet with evidence references →human-approver
03 · authority
Grant the run only what this case needs.
Source material is read-only. Drafts land in a case-specific output path. Tools may read or propose; the human gate owns the external write.
case inputs
workspace/engineering/technical-runbook-refresh/inputs/**Read only the evidence attached to this workflow instance.
case outputs
workspace/engineering/technical-runbook-refresh/outputs/**Write drafts and evidence artifacts without modifying source records.
approved tools
engineering:technical-runbook-refresh:read-or-proposeInvoke only tools explicitly granted for this run; external writes remain gated.
04 · implementation
A private, bounded starting manifest.
The blueprint starts private, caps its DAG, disables replanning, and exposes no public endpoint. Add only the tools and data adapters this workflow has approved.
a2a.yamlsafe starting point
name: engineering-technical-runbook-refresh
version: 0.1.0
entrypoint: agent:BlueprintAgent
expose:
public: false
composition:
planning: deterministic_dag
max_nodes: 6
max_parallel: 1
max_replans: 005 · acceptance test
Pass only with evidence.
- 01
Evidence traceability
Every material conclusion cites an input artifact or a scoped tool result from this run.
- 02
Every proposed instruction maps to current service evidence and includes a safe verification step.
Every proposed instruction maps to current service evidence and includes a safe verification step.
- 03
Approval boundary
The run stops at a proposal and records the human decision before any external side effect.
failure containment
Stop small. Preserve the evidence.
The live service state cannot be reconciled with the documented ownership boundary.
Containment: Return a partial result with unresolved items; do not broaden scope or perform an external write.
Operator: Attach the missing evidence, narrow the brief, or explicitly approve a new scoped run.
A required input or tool grant is unavailable.
Containment: Stop the affected branch and preserve completed artifacts in the case output workspace.
Operator: Grant only the missing resource or continue with that branch marked out of scope.
06 · proof
Sign the run facts. Keep money in the billing ledger.
Current platform receipts sign caller identity or classification, skill, bounded input evidence, verified grant IDs when present, outcome or result preview, and timing. Optional file, tool, artifact, handoff, evaluation, and review fields require separate instrumentation and are not populated by default. Price, fees, payouts, and later human approvals remain separate platform records.
The example uses only fields populated by the current platform sealing paths. It is illustrative, not a record of a real customer run.
ExecutionReceipt · selected fieldsEd25519 token
{
"receipt_id": "rcpt_01J...",
"schema_version": 1,
"agent_name": "engineering-technical-runbook-refresh",
"caller": "user:workflow-owner",
"task_id": "case_technical_runbook_refresh",
"skill_name": "technical_runbook_refresh",
"input_hash": "4d7c...9a2f",
"grant_ids": [
"grt_case_inputs",
"grt_tool_propose"
],
"status": "ok",
"result_preview": "Output prepared: Staleness report. Human decision remains separate.",
"elapsed_ms": 4218
}related blueprints
Keep the operating model consistent.
Engineering
Production incident triage
Correlate an alert with deploy and service evidence, rank hypotheses, and hand an incident commander a bounded action packet.
Engineering
Pull request risk review
Review a proposed change against its tests, ownership boundaries, and operational risk before a maintainer merges it.
Engineering
Flaky test diagnosis
Cluster repeated failures, isolate timing or state signals, and propose the smallest experiment that can confirm the cause.
put the pattern to work
Start private. Scope the authority. Require the decision.
Deploy the workflow as a bounded internal agent, verify its outputs and the receipt fields actually emitted, then expand only the scopes your acceptance test proves it needs.