Evidence the run may read
- Invoice record
- Purchase and receipt evidence
- Vendor and exception policy
Compare an invoice exception with purchase, receipt, and policy evidence and prepare a resolution recommendation.
Search intent: AI agent for invoice exception handling
An invoice fails an approved validation or match rule.
finance owner
An accounts-payable owner approves any posting, hold release, or vendor communication.
invoice exception cycle time (days). Measure exception creation to approved disposition.
Each stage produces an artifact another stage can inspect. The final node is a person, not an autonomous write to an external system.
Validate and normalize the invoice exception review inputs.
Produce the exception explanation.
Produce the evidence comparison table.
Challenge the invoice exception review result and prepare an approval packet.
An accounts-payable owner approves any posting, hold release, or vendor communication.
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.
workspace/finance/invoice-exception-review/inputs/**Read only the evidence attached to this workflow instance.
workspace/finance/invoice-exception-review/outputs/**Write drafts and evidence artifacts without modifying source records.
finance:invoice-exception-review:read-or-proposeInvoke only tools explicitly granted for this run; external writes remain gated.
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.
name: finance-invoice-exception-review
version: 0.1.0
entrypoint: agent:BlueprintAgent
expose:
public: false
composition:
planning: deterministic_dag
max_nodes: 6
max_parallel: 1
max_replans: 0Every material conclusion cites an input artifact or a scoped tool result from this run.
The recommendation reconciles amounts, entities, dates, and supporting evidence without inventing missing records.
The run stops at a proposal and records the human decision before any external side effect.
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.
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.
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.
{
"receipt_id": "rcpt_01J...",
"schema_version": 1,
"agent_name": "finance-invoice-exception-review",
"caller": "user:workflow-owner",
"task_id": "case_invoice_exception_review",
"skill_name": "invoice_exception_review",
"input_hash": "4d7c...9a2f",
"grant_ids": [
"grt_case_inputs",
"grt_tool_propose"
],
"status": "ok",
"result_preview": "Output prepared: Exception explanation. Human decision remains separate.",
"elapsed_ms": 4218
}Evaluate an expense packet against the applicable policy and prepare a cited decision for a human approver.
Compare ledger and subledger evidence, identify unmatched items, and prepare a reconciliation packet for sign-off.
Match a payment export to open receivables and prepare proposed applications with confidence and exceptions.
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.