Skip to main content
Tests show how an AI Agent will handle realistic support cases. Run history shows what it did after a test or live trigger. Open run history to inspect executions across all agents.

​
What to test

Test the agent with messages that represent real customer situations:
  • the happy path the agent should handle
  • messages that should escalate
  • ambiguous customer requests
  • missing order or customer data
  • sensitive actions that require approval
  • messages that should not trigger the agent

​
Test unsaved changes

You do not need to save the agent before you create or run tests. Open AI Agents, open the agent, then select Tests. Create tests and Run tests use the draft in the editor: instructions, actions, and triggers. Live tickets still use the last saved agent. When the draft has unsaved changes, the Tests tab, the run dialog, and the test run show a notice so you know which version is under test.
Save the agent only when you want live tickets to use the new version.

​
Test ownership and hand-offs

Use a short ticket conversation for each case: Also test a later customer message after a human hand-off. It may be matched to an eligible AI Agent again. If the ticket must stay human-only, test after narrowing or disabling every matching AI Agent trigger.

​
Create useful test cases

1

Start from real tickets

Use real customer wording when possible. Short synthetic prompts often miss the details that make support cases hard.
2

Add expected behavior

Define what the agent should do: answer, ask a follow-up, use an action, request approval, or escalate.
3

Include negative cases

Add examples where the agent should not act.
4

Review action usage

Check that the agent uses only the actions needed for the case.
5

Retest after changes

Rerun the relevant cases after changing instructions, triggers, skills, actions, or approvals.

​
Use run history

Use it to check:
  • why this agent received the ticket
  • which instructions and skills influenced the run
  • which actions the agent used
  • whether approval was requested
  • what customer-facing reply was produced
  • why the agent escalated or stopped
The public run history link covers all agents. Agent-specific URLs contain private IDs and should not be published. Open an agent from the AI Agents overview, then select Runs or Tests.

​
Debug unexpected behavior

If a run did not behave as expected, check:
  • whether another automation already owned the conversation
  • whether an exact or meaning-based trigger selected a different agent
  • whether the agent instructions were too broad
  • whether a skill contained conflicting guidance
  • whether the needed action was enabled
  • whether approval blocked the final step
  • whether the ticket lacked required customer or order context
Ask Torben to diagnose the run. Include the ticket number, agent name, or run so Ask Torben can find the relevant execution. For selection problems, read Routing and ownership.

​
Best practices

  • Test before activation and after every major instruction or action change. You can retest the unsaved draft first, then save when the result looks right.
  • Keep approval on while you review early production runs.
  • Add a negative test whenever the agent overreaches.
  • Use run history to improve instructions, not just to debug failures.