Evidence the run may read
- Sanitized ticket themes
- Approved knowledge index
- Escalation and resolution summary
production blueprint · customer support & success
Support knowledge gap detection agent blueprint.
Compare recurring support questions with approved knowledge coverage and propose prioritized article gaps.
Search intent: AI agent for support knowledge gaps
Published by a2a cloudProduct-source methodology →
01 · the contract
Start from a bounded job, not a blank chat box.
trigger
A scheduled support-content review begins.
owner
customer experience owner
agent stops at
The knowledge owner approves article priority, assignment, and publication.
KPI · decrease
repeat contacts for documented issues (percent). Measure repeat contacts after approved gap articles publish.
outputs
Artifacts the run must produce
- Uncovered question clusters
- Article brief proposals
- Priority and owner list
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 support knowledge gap detection inputs.
- 02
question clusterer
Produce the uncovered question clusters.
- 03
coverage mapper
Produce the article brief proposals.
- 04
knowledge manager reviewer
Challenge the support knowledge gap detection result and prepare an approval packet.
- 05
customer experience owner
The knowledge owner approves article priority, assignment, and publication.
intake→ validated input packet →question-clusterer
question-clusterer→ Uncovered question clusters →coverage-mapper
coverage-mapper→ Article brief proposals →knowledge-manager-reviewer
knowledge-manager-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/customer-success/knowledge-gap-detection/inputs/**Read only the evidence attached to this workflow instance.
case outputs
workspace/customer-success/knowledge-gap-detection/outputs/**Write drafts and evidence artifacts without modifying source records.
approved tools
customer-success:knowledge-gap-detection: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: customer-success-knowledge-gap-detection
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
A gap is backed by representative cases and is not already covered by current approved content.
A gap is backed by representative cases and is not already covered by current approved content.
- 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.
Ticket samples are too sparse or sanitized context removes the distinction between problems.
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": "customer-success-knowledge-gap-detection",
"caller": "user:workflow-owner",
"task_id": "case_knowledge_gap_detection",
"skill_name": "knowledge_gap_detection",
"input_hash": "4d7c...9a2f",
"grant_ids": [
"grt_case_inputs",
"grt_tool_propose"
],
"status": "ok",
"result_preview": "Output prepared: Uncovered question clusters. Human decision remains separate.",
"elapsed_ms": 4218
}related blueprints
Keep the operating model consistent.
Customer Support & Success
Customer support ticket triage
Classify a customer issue, identify missing context, and route it with an evidence-backed urgency proposal.
Customer Support & Success
Support response draft
Draft a clear answer from approved knowledge and case evidence, with uncertainty and escalation stated explicitly.
Customer Support & Success
Refund request review
Compare a refund request with policy, transaction, usage, and prior-case evidence and prepare a decision packet.
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.