a2a cloud
production blueprint · people operations

Employee offboarding coordination agent blueprint.

Build a confidential owner-assigned departure checklist spanning people, payroll, assets, access, and knowledge transfer.

Search intent: AI agent for employee offboarding coordination

Published by a2a cloudProduct-source methodology →
01 · the contract

Start from a bounded job, not a blank chat box.

trigger

An authorized departure event enters the people-operations workflow.

owner

people operations owner

agent stops at

People operations approves timing and communications; each owner approves actions in their system.

KPI · increase

offboarding tasks completed within policy (percent). Measure authorized departures with every required task completed by its approved deadline.

inputs

Evidence the run may read

  • Approved departure record
  • Applicable policy and agreement checklist
  • Manager, payroll, IT, and asset ownership context
outputs

Artifacts the run must produce

  • People offboarding plan
  • Cross-functional owner matrix
  • Sensitive exception and completion register
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.

  1. 01

    intake

    Validate and normalize the employee offboarding coordination inputs.

  2. 02

    policy checklist mapper

    Produce the people offboarding plan.

  3. 03

    cross-functional coordinator

    Produce the cross-functional owner matrix.

  4. 04

    people operations reviewer

    Challenge the employee offboarding coordination result and prepare an approval packet.

  5. 05

    people operations owner

    People operations approves timing and communications; each owner approves actions in their system.

intakevalidated input packetpolicy-checklist-mapper
policy-checklist-mapperPeople offboarding plancross-functional-coordinator
cross-functional-coordinatorCross-functional owner matrixpeople-operations-reviewer
people-operations-reviewerapproval packet with evidence referenceshuman-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.

read

case inputs

workspace/people-ops/employee-offboarding-coordination/inputs/**

Read only the evidence attached to this workflow instance.

write-output

case outputs

workspace/people-ops/employee-offboarding-coordination/outputs/**

Write drafts and evidence artifacts without modifying source records.

invoke-scoped-tool

approved tools

people-ops:employee-offboarding-coordination:read-or-propose

Invoke only tools explicitly granted for this run; external writes remain gated.

required human decision

People operations approves timing and communications; each owner approves actions in their system.

Decision owner: people operations owner.

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: people-ops-employee-offboarding-coordination
version: 0.1.0
entrypoint: agent:BlueprintAgent
expose:
  public: false
composition:
  planning: deterministic_dag
  max_nodes: 6
  max_parallel: 1
  max_replans: 0
05 · acceptance test

Pass only with evidence.

  1. 01

    Evidence traceability

    Every material conclusion cites an input artifact or a scoped tool result from this run.

  2. 02

    The plan exposes only minimum necessary information and does not autonomously disable access, alter pay, or contact the employee.

    The plan exposes only minimum necessary information and does not autonomously disable access, alter pay, or contact the employee.

  3. 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.

Departure authority, timing, jurisdiction, agreement terms, or accountable system owners are unresolved.

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": "people-ops-employee-offboarding-coordination",
  "caller": "user:workflow-owner",
  "task_id": "case_employee_offboarding_coordination",
  "skill_name": "employee_offboarding_coordination",
  "input_hash": "4d7c...9a2f",
  "grant_ids": [
    "grt_case_inputs",
    "grt_tool_propose"
  ],
  "status": "ok",
  "result_preview": "Output prepared: People offboarding plan. Human decision remains separate.",
  "elapsed_ms": 4218
}
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.