Evidence the run may read
- Sample request
- Approved transaction and control evidence
- Evidence retention policy
production blueprint · finance
Finance audit sample packet agent blueprint.
Collect the approved records for an audit sample, index them, and identify missing evidence before reviewer release.
Search intent: AI agent for financial audit evidence
Published by a2a cloudProduct-source methodology →
01 · the contract
Start from a bounded job, not a blank chat box.
trigger
An auditor or internal reviewer selects a finance sample.
owner
finance owner
agent stops at
The audit liaison approves completeness and external release.
KPI · increase
audit sample first-pass acceptance (percent). Measure released samples accepted without a follow-up evidence request.
outputs
Artifacts the run must produce
- Indexed evidence packet
- Completeness checklist
- Missing-item 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 finance audit sample packet inputs.
- 02
sample interpreter
Produce the indexed evidence packet.
- 03
evidence collector
Produce the completeness checklist.
- 04
audit liaison reviewer
Challenge the finance audit sample packet result and prepare an approval packet.
- 05
finance owner
The audit liaison approves completeness and external release.
intake→ validated input packet →sample-interpreter
sample-interpreter→ Indexed evidence packet →evidence-collector
evidence-collector→ Completeness checklist →audit-liaison-reviewer
audit-liaison-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/finance/audit-sample-packet/inputs/**Read only the evidence attached to this workflow instance.
case outputs
workspace/finance/audit-sample-packet/outputs/**Write drafts and evidence artifacts without modifying source records.
approved tools
finance:audit-sample-packet: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: finance-audit-sample-packet
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
Each requested attribute maps to a specific dated source artifact with no unsupported substitution.
Each requested attribute maps to a specific dated source artifact with no unsupported substitution.
- 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.
Requested evidence is unavailable, outside retention, or restricted from external release.
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": "finance-audit-sample-packet",
"caller": "user:workflow-owner",
"task_id": "case_audit_sample_packet",
"skill_name": "audit_sample_packet",
"input_hash": "4d7c...9a2f",
"grant_ids": [
"grt_case_inputs",
"grt_tool_propose"
],
"status": "ok",
"result_preview": "Output prepared: Indexed evidence packet. Human decision remains separate.",
"elapsed_ms": 4218
}related blueprints
Keep the operating model consistent.
Finance
Invoice exception review
Compare an invoice exception with purchase, receipt, and policy evidence and prepare a resolution recommendation.
Finance
Expense policy review
Evaluate an expense packet against the applicable policy and prepare a cited decision for a human approver.
Finance
Month-end reconciliation support
Compare ledger and subledger evidence, identify unmatched items, and prepare a reconciliation packet for sign-off.
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.