Scope
This guide covers automation for Agent Approvals. Availability depends on your tenant package, role and configured providers.
Purpose
Keep proposed AI work behind explicit human decisions.
Route completed agent work into approval queues.
Before you start
Correct tenant and project selected
Required source or provider is available
An accountable owner is identified
Test data can be separated from live activity
Procedure
- Complete the manual workflow successfully before enabling repeat execution.
- Route completed agent work into approval queues.
- Define the trigger, eligibility conditions, action and intended output.
- Add a failure path, owner, retry rule and stop condition.
- Run a controlled test and inspect every generated record or delivery event.
- Keep the automation bounded: Preserve reviewer, decision, evidence and timestamps.
Verify the result
Measure acceptance, revisions, rejections and follow-through. Confirm that the intended record, state, run or report is visible to another authorised operator and that its next owner is clear.
Completion checkpoint
The capability is in the intended state, evidence is current, exceptions are owned and the next action can be understood without a separate status message.
Controls and limitations
Preserve reviewer, decision, evidence and timestamps. Predictive, attribution and recommendation outputs support operator judgement; provider and data limitations remain relevant.