Evidence the run may read
- Approved role and manager
- Start date and location
- Role-based access catalog
production blueprint · it
Employee onboarding access plan agent blueprint.
Translate an approved role and start-date packet into a least-privilege access and equipment checklist.
Search intent: AI agent for employee IT onboarding
Published by a2a cloudProduct-source methodology →
01 · the contract
Start from a bounded job, not a blank chat box.
trigger
An approved new-hire onboarding request is submitted.
owner
IT service owner
agent stops at
The manager and each resource owner approve access before provisioning.
KPI · increase
day-one IT readiness (percent). Measure approved hires with required IT resources ready by start time.
outputs
Artifacts the run must produce
- Access request checklist
- Equipment and account plan
- Unresolved approvals list
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 employee onboarding access plan inputs.
- 02
role mapper
Produce the access request checklist.
- 03
access planner
Produce the equipment and account plan.
- 04
onboarding reviewer
Challenge the employee onboarding access plan result and prepare an approval packet.
- 05
IT service owner
The manager and each resource owner approve access before provisioning.
intake→ validated input packet →role-mapper
role-mapper→ Access request checklist →access-planner
access-planner→ Equipment and account plan →onboarding-reviewer
onboarding-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/it/employee-onboarding-access-plan/inputs/**Read only the evidence attached to this workflow instance.
case outputs
workspace/it/employee-onboarding-access-plan/outputs/**Write drafts and evidence artifacts without modifying source records.
approved tools
it:employee-onboarding-access-plan: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: it-employee-onboarding-access-plan
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
Every requested entitlement maps to the approved role or an explicit owner exception.
Every requested entitlement maps to the approved role or an explicit owner exception.
- 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 role template is missing, ambiguous, or conflicts with segregation-of-duties policy.
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": "it-employee-onboarding-access-plan",
"caller": "user:workflow-owner",
"task_id": "case_employee_onboarding_access_plan",
"skill_name": "employee_onboarding_access_plan",
"input_hash": "4d7c...9a2f",
"grant_ids": [
"grt_case_inputs",
"grt_tool_propose"
],
"status": "ok",
"result_preview": "Output prepared: Access request checklist. Human decision remains separate.",
"elapsed_ms": 4218
}related blueprints
Keep the operating model consistent.
IT
Help desk ticket triage
Classify a ticket, gather relevant approved knowledge, and prepare a routed resolution packet for the service desk.
IT
Offboarding revocation plan
Build a time-bounded account, device, token, and ownership-transfer checklist from approved departure data.
IT
Software access request review
Check a software entitlement request against role need, licensing, conflicts, and owner policy before approval.
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.