Evidence the run may read
- Approved outcome and usage summary
- Support and project history
- Account goals and open actions
production blueprint · customer support & success
Quarterly business review preparation agent blueprint.
Assemble approved outcomes, usage, support themes, and open decisions into a sourced QBR narrative.
Search intent: AI agent for QBR preparation
Published by a2a cloudProduct-source methodology →
01 · the contract
Start from a bounded job, not a blank chat box.
trigger
An account reaches its QBR preparation window.
owner
customer experience owner
agent stops at
The account owner approves every customer-facing metric, claim, and recommendation.
KPI · decrease
QBR preparation time (hours). Measure analyst and account-owner time to approved QBR packet.
outputs
Artifacts the run must produce
- Outcome scorecard
- Sourced QBR narrative
- Decision-oriented agenda
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 quarterly business review preparation inputs.
- 02
outcome analyst
Produce the outcome scorecard.
- 03
narrative composer
Produce the sourced qbr narrative.
- 04
account reviewer
Challenge the quarterly business review preparation result and prepare an approval packet.
- 05
customer experience owner
The account owner approves every customer-facing metric, claim, and recommendation.
intake→ validated input packet →outcome-analyst
outcome-analyst→ Outcome scorecard →narrative-composer
narrative-composer→ Sourced QBR narrative →account-reviewer
account-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/quarterly-business-review/inputs/**Read only the evidence attached to this workflow instance.
case outputs
workspace/customer-success/quarterly-business-review/outputs/**Write drafts and evidence artifacts without modifying source records.
approved tools
customer-success:quarterly-business-review: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-quarterly-business-review
version: 0.1.0
entrypoint: agent:BlueprintAgent
expose:
public: false
composition:
planning: deterministic_dag
max_nodes: 6
max_parallel: 3
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
Metrics use a consistent period and definition; narrative claims link to approved account evidence.
Metrics use a consistent period and definition; narrative claims link to approved account evidence.
- 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.
Outcome baselines or metric definitions changed without a documented bridge.
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-quarterly-business-review",
"caller": "user:workflow-owner",
"task_id": "case_quarterly_business_review",
"skill_name": "quarterly_business_review",
"input_hash": "4d7c...9a2f",
"grant_ids": [
"grt_case_inputs",
"grt_tool_propose"
],
"status": "ok",
"result_preview": "Output prepared: Outcome scorecard. 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.