Evidence the run may read
- Purchase order and exception
- Request, approval, and receipt evidence
- Purchasing policy
production blueprint · procurement
Purchase order exception review agent blueprint.
Compare a purchase-order exception with request, approval, receipt, and policy evidence and prepare a bounded disposition.
Search intent: AI agent for purchase order exceptions
Published by a2a cloudProduct-source methodology →
01 · the contract
Start from a bounded job, not a blank chat box.
trigger
A purchase order fails an approved amount, match, timing, or policy rule.
owner
procurement owner
agent stops at
An authorized purchasing or finance owner approves any correction, release, or exception.
KPI · decrease
purchase order exception age (days). Measure exception creation to authorized disposition.
outputs
Artifacts the run must produce
- Exception cause table
- Missing evidence and owner list
- Correct, return, or escalate proposal
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 purchase order exception review inputs.
- 02
transaction normalizer
Produce the exception cause table.
- 03
policy and evidence analyst
Produce the missing evidence and owner list.
- 04
purchasing reviewer
Challenge the purchase order exception review result and prepare an approval packet.
- 05
procurement owner
An authorized purchasing or finance owner approves any correction, release, or exception.
intake→ validated input packet →transaction-normalizer
transaction-normalizer→ Exception cause table →policy-and-evidence-analyst
policy-and-evidence-analyst→ Missing evidence and owner list →purchasing-reviewer
purchasing-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/procurement/purchase-order-exception-review/inputs/**Read only the evidence attached to this workflow instance.
case outputs
workspace/procurement/purchase-order-exception-review/outputs/**Write drafts and evidence artifacts without modifying source records.
approved tools
procurement:purchase-order-exception-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: procurement-purchase-order-exception-review
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
The recommendation reconciles entity, supplier, amount, currency, approval, and receipt evidence.
The recommendation reconciles entity, supplier, amount, currency, approval, and receipt 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.
The underlying request, approval authority, receipt, or supplier record cannot be verified.
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": "procurement-purchase-order-exception-review",
"caller": "user:workflow-owner",
"task_id": "case_purchase_order_exception_review",
"skill_name": "purchase_order_exception_review",
"input_hash": "4d7c...9a2f",
"grant_ids": [
"grt_case_inputs",
"grt_tool_propose"
],
"status": "ok",
"result_preview": "Output prepared: Exception cause table. Human decision remains separate.",
"elapsed_ms": 4218
}related blueprints
Keep the operating model consistent.
Procurement
Purchase request triage
Normalize a purchase request, identify missing business and approval context, and route it under the approved buying policy.
Procurement
Supplier discovery brief
Translate an approved sourcing need into neutral requirements, research questions, and a reviewer-controlled supplier discovery plan.
Procurement
Vendor comparison
Compare supplier responses against approved requirements and produce an evidence-linked matrix without choosing the winner.
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.