Evidence the run may read
- Control and period definition
- Approved evidence source index
- Owner and retention guidance
Map a control request to approved sources, collect a bounded evidence packet, and flag missing attestations.
Search intent: AI agent for compliance evidence collection
A scheduled control test or evidence request opens.
compliance owner
The control owner attests completeness and approves release to testing or audit.
evidence requests accepted first pass (percent). Measure packets accepted without a completeness follow-up.
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 control evidence collection inputs.
Produce the indexed evidence packet.
Produce the control-to-evidence map.
Challenge the control evidence collection result and prepare an approval packet.
The control owner attests completeness and approves release to testing or audit.
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/compliance/control-evidence-collection/inputs/**Read only the evidence attached to this workflow instance.
workspace/compliance/control-evidence-collection/outputs/**Write drafts and evidence artifacts without modifying source records.
compliance:control-evidence-collection: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: compliance-control-evidence-collection
version: 0.1.0
entrypoint: agent:BlueprintAgent
expose:
public: false
composition:
planning: deterministic_dag
max_nodes: 6
max_parallel: 3
max_replans: 0Every material conclusion cites an input artifact or a scoped tool result from this run.
Every artifact has source, period, owner, retrieval date, and direct control relevance.
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": "compliance-control-evidence-collection",
"caller": "user:workflow-owner",
"task_id": "case_control_evidence_collection",
"skill_name": "control_evidence_collection",
"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
}Translate an audit request into attributes, sources, owners, and an approved response packet without over-answering scope.
Map approved policy statements to controls and evidence expectations, highlighting unsupported or orphaned requirements.
Select or ingest an approved sample and assemble entitlement, approval, and change evidence for control testing.
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.