# Test your AI before customers do

Use realistic questions in Playground to verify answers, uncertainty, and human handoff behavior.

- **Audience:** Workspace administrators approving AI behavior before launch
- **Intent:** Get started
- **Active work:** 10 minutes
- **Waiting:** None
- **Where this happens:** Complete this in Onlo Playground. No customer will see these tests.

Canonical page: https://onlo.ai/docs/guides/get-started/test-ai

## Before you start

- At least one Fresh source in Knowledge base
- Three realistic customer questions: one known answer, one uncertain case, and one human handoff case

## Why test the AI?

Playground lets you find missing knowledge and unsafe behavior before customers encounter it. Test outcomes, not polished demo questions.

## Run three representative tests

1. **Open Playground.** In Onlo, open AI setup → Playground and choose the customer channel you want to simulate.
   - **Expected result:** The composer and the selected channel appear.
2. **Enable the intended scope.** Confirm Knowledge base is enabled. Include Playbooks only when the scenario should use one.
   - **Expected result:** The test uses the same sources and workflows you intend to evaluate.
3. **Ask a known question.** Ask a question whose correct answer exists in the Fresh source you added.
   - **Expected result:** The reply matches the source and the trace shows the relevant knowledge.
4. **Ask an unsupported question.** Ask for information your sources do not contain.
   - **Expected result:** The AI asks for clarification, states uncertainty, or follows your configured fallback instead of inventing an answer.
5. **Ask for a person.** Use a message that should trigger your human handoff behavior.
   - **Expected result:** The response follows the configured escalation or handoff path.

### Expected result

Repeat the known, unsupported, and handoff scenarios once without changing configuration.

**Success:** All three scenarios produce the intended answer or fallback behavior consistently.

**If you do not see this:**

- For a wrong known answer, inspect the cited source and remove conflicting or obsolete content.
- For an invented answer, review AI settings and make the fallback behavior more explicit.
- For a failed handoff, verify the escalation condition and the teammate who should receive it.

## Customer questions

### Does Playground use workspace credits?

The current Playground labels its test usage as free and shows an estimated production cost for context.

### How many questions should I test?

Start with the three behavior types in this guide. Add real support questions as your team discovers gaps.

### What should I fix first?

Fix confident incorrect answers and broken handoffs before improving tone or response style.

## Common mistakes

- Testing only questions copied directly from the source headings.
- Treating a fluent answer as correct without checking the source or trace.
- Skipping the unsupported and human handoff scenarios.

## You have completed this guide when

- [ ] A known question receives an accurate answer from the intended knowledge.
- [ ] An unsupported question does not produce a confident invented answer.
- [ ] A handoff request follows the behavior configured for your team.

## Troubleshooting

### The AI does not use the new source.

**Likely cause:** Knowledge base is disabled in the test scope or the source does not closely match the question.

**Recovery:** Enable Knowledge base, ask a specific question, and confirm the source is Fresh.

### The AI gives a confident wrong answer.

**Likely cause:** The source is unclear, conflicting, or the configured fallback allows an unsupported response.

**Recovery:** Inspect the trace, correct the owning source, and repeat the same question.

### The AI never hands off.

**Likely cause:** The test does not match the escalation condition or no valid teammate path is configured.

**Recovery:** Review the handoff condition and responsible teammate, then repeat the exact scenario.

## Related pages

- [Invite teammates to your workspace](https://onlo.ai/docs/guides/get-started/invite-teammates): Invite the people who will answer conversations, review work, and receive human handoffs.