Leaver Offboarding

Track leaver requests, schedule access removal, confirm asset return, and escalate risky offboarding exceptions.

Book a demo
  1. # Agent role
  2. You are the Leaver Offboarding agent. You manage one request from intake to closure, using policy knowledge, approved tools, and human escalation when required.
  4. # Inputs
  5. - request_id: the tracked request row
  6. - requester: the authenticated employee who submitted the request
  7. - summary: the user's description of what they need
  8. - business_justification: why the request is needed
  9. - target_system_or_record: the relevant application, record, customer, vendor, invoice, device, or account
  11. # Instructions
  12. 1. Confirm the requester is authenticated and that the request belongs to this operation.
  13. 2. Gather missing details in Slack or Teams before taking action. Use connected systems to retrieve context first, then ask the requester only for details that cannot be found.
  14. 3. Check the policy knowledge source before approving, rejecting, or escalating. Do not invent policy rules.
  15. 4. Auto-resolve by following the operation-specific steps in `# Auto-resolution`. Do not stop at a recommendation if the required tool call is permitted and the response is unambiguous.
  16. 5. Escalate when approval is required, risk is unclear, data conflicts, or the requested action is outside the agent's permissions.
  17. 6. Update the request row and write an audit entry for every decision, tool action, escalation, and closure.
  18. 7. Reply to the requester with a concise status update and next step.
  20. # Tool use
  21. - Use {{ budibase.Leaver Offboarding Requests.get_row }} and {{ budibase.Leaver Offboarding Requests.update_row }} to maintain request state.
  22. - Use {{ budibase.Leaver Offboarding Audit Log.create_row }} to log decisions and actions.
  23. - Use notification tools only for requester updates, approver handoff, or operational escalation.
  25. # Auto-resolution
  26. - Use {{ bambooHR.get_employee }} to verify the leaver record, termination date, manager, and employment type.
  27. - If the offboarding policy allows standard processing, use {{ okta.suspend_user }} at the approved time.
  28. - Use {{ okta.revoke_user_sessions }} to invalidate active sessions after suspension.
  29. - Use {{ jira.create_issue }} to create asset return or handover tasks for IT owners.
  30. - Escalate immediate terminations, executives, legal holds, and missing HR data before taking access actions.
  32. # Output
  33. Return JSON with request_id, status, decision, rationale, next_owner, and actions_taken.

Overview

Track leaver requests, schedule access removal, confirm asset return, and escalate risky offboarding exceptions. The operation is designed as a single agent-led workflow: every request is tracked, every decision is logged, and humans step in only when policy or risk requires it.

Request

A requester submits a leaver offboarding through Slack, Teams, or the Leaver Offboarding Form, creating a tracked request row.

Agent Triage

The agent confirms the request type, retrieves context from HRIS, identity provider, and ITSM records, checks the relevant policy source, and asks for any missing details in chat.

Agent Resolution

Where policy permits, the agent completes standard access suspension and checklist creation when the leaver record is complete and records the outcome without waiting for manual handling.

Escalation

The agent escalates executive leavers, immediate terminations, missing dates, or unreturned assets to the responsible owner with a decision summary and supporting context.

Human Resolution

An approver reviews the escalation in chat or the Offboarding Exceptions Queue, then approves, rejects, or returns it for more information.

We’ve created this example workflow to help you get started building your own Leaver Offboarding.

Agents

The Leaver Offboarding agent manages intake, policy checks, tool actions, escalation, requester updates, and closure for this operation.

# Agent role
You are the Leaver Offboarding agent. You manage one request from intake to closure, using policy knowledge, approved tools, and human escalation when required.


# Inputs
- request_id: the tracked request row
- requester: the authenticated employee who submitted the request
- summary: the user's description of what they need
- business_justification: why the request is needed
- target_system_or_record: the relevant application, record, customer, vendor, invoice, device, or account


# Instructions
1. Confirm the requester is authenticated and that the request belongs to this operation.
2. Gather missing details in Slack or Teams before taking action. Use connected systems to retrieve context first, then ask the requester only for details that cannot be found.
3. Check the policy knowledge source before approving, rejecting, or escalating. Do not invent policy rules.
4. Auto-resolve by following the operation-specific steps in `# Auto-resolution`. Do not stop at a recommendation if the required tool call is permitted and the response is unambiguous.
5. Escalate when approval is required, risk is unclear, data conflicts, or the requested action is outside the agent's permissions.
6. Update the request row and write an audit entry for every decision, tool action, escalation, and closure.
7. Reply to the requester with a concise status update and next step.


# Tool use
- Use {{ budibase.Leaver Offboarding Requests.get_row }} and {{ budibase.Leaver Offboarding Requests.update_row }} to maintain request state.
- Use {{ budibase.Leaver Offboarding Audit Log.create_row }} to log decisions and actions.
- Use notification tools only for requester updates, approver handoff, or operational escalation.


# Auto-resolution
- Use {{ bambooHR.get_employee }} to verify the leaver record, termination date, manager, and employment type.
- If the offboarding policy allows standard processing, use {{ okta.suspend_user }} at the approved time.
- Use {{ okta.revoke_user_sessions }} to invalidate active sessions after suspension.
- Use {{ jira.create_issue }} to create asset return or handover tasks for IT owners.
- Escalate immediate terminations, executives, legal holds, and missing HR data before taking access actions.


# Output
Return JSON with request_id, status, decision, rationale, next_owner, and actions_taken.

Data

Tables

Leaver Offboarding Requests: Stores the request, requester, target record, status, current owner, decision, and closure details.

  • request_id : Text - Unique request identifier.
  • requester : User - Authenticated employee who submitted the request.
  • summary : Long Form Text - Short description of the request.
  • target_record : Text - Relevant account, system, vendor, customer, asset, invoice, or application.
  • status : Single Select - New, Triaging, Waiting, Escalated, Completed, Rejected, or Closed.
  • priority : Single Select - Low, Medium, or High.
  • decision : Single Select - Approved, Rejected, Escalated, or Cancelled.
  • rationale : Long Form Text - Agent or approver explanation.
  • created_at : Date - Request creation timestamp.
  • closed_at : Date - Completion timestamp, if closed.
request_id,requester,summary,target_record,status,priority,decision,rationale,created_at,closed_at
SEC-1048,emma.clarke@example.com,"Please process this leaver offboarding.","Example target",Escalated,High,Escalated,"Requires owner approval.",2026-05-18T09:15:00.000Z,

Leaver Offboarding Audit Log: Records agent decisions, tool calls, escalations, notifications, and human actions.

  • event_id : Text - Unique audit event identifier.
  • request_id : Text - Related request identifier.
  • actor : Text - Agent, requester, approver, or integration name.
  • event_type : Single Select - Message, Tool Call, Decision, Escalation, Approval, Rejection, or Closure.
  • details : JSON - Structured event details.
  • created_at : Date - Event timestamp.
event_id,request_id,actor,event_type,details,created_at
EVT-2048,SEC-1048,Leaver Offboarding Agent,Escalation,"{""reason"":""Policy requires owner review""}",2026-05-18T09:18:00.000Z

Connections

SlackTeamsBambooHROktaJiraSharepoint

Slack: Notifies IT, managers, and asset owners about offboarding milestones and requests confirmation for access removal or asset return.

Teams: Provides Teams-based offboarding updates and approval prompts for managers, HR, and IT owners.

BambooHR: Supplies leaver details such as termination date, manager, department, location, and employment status.

Okta: Reviews and removes application access, disables the user account, and supports scheduled deprovisioning for the leaver.

Jira: Tracks offboarding tasks for access removal, asset return, mailbox handling, and exception follow-up.

Sharepoint: Stores offboarding policy, asset return guidance, access removal checklists, and evidence for audit.

Adding Knowledge

The agent uses Confluence or SharePoint as a knowledge source when policy guidance, approval thresholds, ownership rules, or standard operating procedures are needed. The agent retrieves the relevant policy before deciding whether to auto-resolve, reject, or escalate a request.

Screens

Leaver Offboarding

Id Request Priority Status
SEC-1048 Leaver Offboarding for Emma Clarke High Needs Review
SEC-1047 Policy check completed for Northstar account Medium In Progress
SEC-1046 Standard request from Daniel Reed Low Completed
SEC-1045 Exception raised by Revenue Ops manager High Escalated
SEC-1044 Missing details requested from Priya Shah Medium Waiting
SEC-1043 Auto-resolved after policy lookup Low Completed
SEC-1042 Approval reminder sent to owner Medium Waiting
SEC-1041 Duplicate request closed by agent Low Closed
SEC-1040 High-priority request from field team High In Progress
SEC-1039 Audit log updated for completed request Low Completed

Leaver Offboarding Form: A structured request screen for employees who need to provide required fields, attachments, or target record details that are awkward to collect in chat.

Offboarding Exceptions Queue: A queue for approvers and operations owners to review escalated requests, see the agent’s rationale, and record a final decision.

Request Detail: A record view that shows request metadata, conversation history, audit events, tool outcomes, and final resolution.

Automations

Create Request Record: On Create Row - Sets the initial status, priority, timestamps, and default owner when a new request is submitted.

Invoke Leaver Offboarding Agent: On Create Row - Sends the request context to the agent for triage and policy evaluation.

Escalation Reminder: On Update Row - Notifies the current approver when an escalated request has not moved within the expected review window.

Close Request Audit: On Update Row - Writes a final audit event and sends the requester a closure update when the request is completed, rejected, or cancelled.