Evidence the run may read
- Approved departure record
- Account and device inventory
- System ownership map
Build a time-bounded account, device, token, and ownership-transfer checklist from approved departure data.
Search intent: AI agent for IT offboarding
An approved employee or contractor departure notice is received.
IT service owner
IT and the manager approve revocations, timing, and ownership transfers.
access revocation completion (percent). Measure approved departures completed within the policy window.
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 offboarding revocation plan inputs.
Produce the revocation sequence.
Produce the asset return checklist.
Challenge the offboarding revocation plan result and prepare an approval packet.
IT and the manager approve revocations, timing, and ownership transfers.
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/it/offboarding-revocation-plan/inputs/**Read only the evidence attached to this workflow instance.
workspace/it/offboarding-revocation-plan/outputs/**Write drafts and evidence artifacts without modifying source records.
it:offboarding-revocation-plan: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: it-offboarding-revocation-plan
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 plan covers known identities and assets without disabling shared or transferred resources prematurely.
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": "it-offboarding-revocation-plan",
"caller": "user:workflow-owner",
"task_id": "case_offboarding_revocation_plan",
"skill_name": "offboarding_revocation_plan",
"input_hash": "4d7c...9a2f",
"grant_ids": [
"grt_case_inputs",
"grt_tool_propose"
],
"status": "ok",
"result_preview": "Output prepared: Revocation sequence. Human decision remains separate.",
"elapsed_ms": 4218
}Classify a ticket, gather relevant approved knowledge, and prepare a routed resolution packet for the service desk.
Translate an approved role and start-date packet into a least-privilege access and equipment checklist.
Check a software entitlement request against role need, licensing, conflicts, and owner policy before approval.
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.