Evidence the run may read
- User question
- Approved knowledge articles
- Service and client-version context
production blueprint · it
IT knowledge base answer draft agent blueprint.
Draft a support answer from current approved articles and highlight where the knowledge base does not support a claim.
Search intent: AI agent for IT knowledge base answers
Published by a2a cloudProduct-source methodology →
01 · the contract
Start from a bounded job, not a blank chat box.
trigger
A service-desk ticket needs a documented answer.
owner
IT service owner
agent stops at
A service-desk reviewer approves the user-facing answer.
KPI · increase
first-contact resolution (percent). Measure reviewed answers that resolve the ticket without reopening.
outputs
Artifacts the run must produce
- Cited answer draft
- Applicability notes
- Knowledge gap flag
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 it knowledge base answer draft inputs.
- 02
intent classifier
Produce the cited answer draft.
- 03
knowledge retriever
Produce the applicability notes.
- 04
support content reviewer
Challenge the it knowledge base answer draft result and prepare an approval packet.
- 05
IT service owner
A service-desk reviewer approves the user-facing answer.
intake→ validated input packet →intent-classifier
intent-classifier→ Cited answer draft →knowledge-retriever
knowledge-retriever→ Applicability notes →support-content-reviewer
support-content-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/it/knowledge-base-answer-draft/inputs/**Read only the evidence attached to this workflow instance.
case outputs
workspace/it/knowledge-base-answer-draft/outputs/**Write drafts and evidence artifacts without modifying source records.
approved tools
it:knowledge-base-answer-draft: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: it-knowledge-base-answer-draft
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 instruction is supported by an approved article applicable to the user's platform and version.
Every instruction is supported by an approved article applicable to the user's platform and version.
- 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.
Available knowledge is outdated, contradictory, or does not cover the user's context.
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": "it-knowledge-base-answer-draft",
"caller": "user:workflow-owner",
"task_id": "case_knowledge_base_answer_draft",
"skill_name": "knowledge_base_answer_draft",
"input_hash": "4d7c...9a2f",
"grant_ids": [
"grt_case_inputs",
"grt_tool_propose"
],
"status": "ok",
"result_preview": "Output prepared: Cited answer draft. Human decision remains separate.",
"elapsed_ms": 4218
}related blueprints
Keep the operating model consistent.
IT
Help desk ticket triage
Classify a ticket, gather relevant approved knowledge, and prepare a routed resolution packet for the service desk.
IT
Employee onboarding access plan
Translate an approved role and start-date packet into a least-privilege access and equipment checklist.
IT
Offboarding revocation plan
Build a time-bounded account, device, token, and ownership-transfer checklist from approved departure data.
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.