# How to Test Your Voice AI Agent

#### <mark style="color:$primary;">**Why Test Your Voice Agent?**</mark>

A voice agent talks to your customers in real time on a phone call. Unlike text, there is no time to review or edit a response before the customer hears it. This makes testing even more important for voice agents than text agents. You need to make sure the agent sounds natural, answers correctly, handles pauses and interruptions well, and transfers to a human when needed.

***

#### <mark style="color:$primary;">**How to Test Your Voice AI Agent**</mark>

Testing a voice agent is different from testing a text agent. Instead of using the Test Chat panel, you make an actual phone call to hear how the agent sounds and responds.

<figure><img src="/files/Mz1Jtg62Jve1DCiO787q" alt=""><figcaption></figcaption></figure>

#### <mark style="color:$primary;">**Step 1 — Assign the AI Agent to Your Chat**</mark>

1. Open your DoubleTick dashboard.
2. Click on Chats in the left navigation panel.
3. Search for your own phone number in the chats list. If it does not exist, start a new chat with your own number.
4. Open the chat with your phone number.
5. Assign the voice AI agent you just created to this chat.

#### <mark style="color:$primary;">**Step 2 — Call the API Number**</mark>

1. From your phone, call your WhatsApp API number — this is the number connected to your DoubleTick account.
2. The call will connect and the AI agent will pick up.
3. The agent will greet you and start the conversation based on your voice instructions.

#### <mark style="color:$primary;">**Step 3 — Test Different Scenarios**</mark>

Once the call is connected, run through the following tests:

**Test 1 — Greeting and Introduction**

1. Listen to the agent's greeting.
2. Does it introduce itself by name?
3. Does it ask how it can help?
4. Does the voice sound natural and clear?

**Test 2 — FAQ Accuracy**

1. Ask a question that is covered in your FAQs.
2. Does the agent answer correctly?
3. Does it speak clearly and at a comfortable pace?
4. Try asking the same question in different ways to check if the agent still understands.

**Test 3 — Unknown Questions**

1. Ask a question that is not in your FAQs or websites.
2. Does the agent say it does not have the information?
3. Does it offer to connect you with a human agent?
4. Make sure it does not make up an answer.

**Test 4 — Information Collection**

1. If you have a Bot Tool that collects parameters (like name, phone, date), trigger it by saying the right phrase — for example, "I want to book a site visit."
2. Does the agent ask for each piece of information one at a time?
3. Does it confirm what you said before moving to the next question?
4. Does the journey trigger correctly after all information is collected?

**Test 5 — Forward to Human**

1. Say "I want to speak to a human" or "Can you transfer me to someone?"
2. Does the agent acknowledge the request?
3. Does it transfer the call to a human agent?

**Test 6 — Language Handling**

1. If you set the voice language to Multilingual, start speaking in one language and switch to another mid-conversation.
2. Does the agent switch languages with you?

**Test 7 — Edge Cases**

1. Stay silent for a few seconds — does the agent handle the pause naturally? Does it prompt you?
2. Interrupt the agent mid-sentence — does it handle the interruption gracefully?
3. Speak in a noisy environment — does the agent still understand you?
4. Ask unrelated questions — does the agent stay within its scope?

**Step 4 — Make Changes Based on Test Results**

After testing, go back to your agent and make adjustments:

<table><thead><tr><th width="272">Issue</th><th>Where to Fix</th></tr></thead><tbody><tr><td>Agent gives wrong answers</td><td>Check FAQs in the Knowledge tab — is the answer there? Is it accurate?</td></tr><tr><td>Agent sounds unnatural or too robotic</td><td>Try a different Voice Name in Settings → Voice</td></tr><tr><td>Agent speaks too fast or too slow</td><td>Adjust the speaking style instructions in Instructions → Voice</td></tr><tr><td>Agent does not understand certain questions</td><td>Add those questions as FAQs in the Knowledge tab</td></tr><tr><td>Agent does not trigger the right tool</td><td>Check the tool's Description in the Tools tab — make it more specific</td></tr><tr><td>Agent does not transfer to human</td><td>Check if Forward to Human is enabled in Settings → Voice and the Talk To Human tool is active</td></tr><tr><td>Agent makes up answers</td><td>Add a clear rule in your voice instructions: "Do not make up information you do not have"</td></tr><tr><td>Agent does not handle silence well</td><td>Add an instruction like: "If the customer is silent for more than 5 seconds, say: Are you still there? How can I help?"</td></tr></tbody></table>

#### <mark style="color:$primary;">**Step 5 — Re-test After Every Change**</mark>

1. After making any changes, repeat the call test.
2. Focus on the specific scenario you fixed.
3. Keep repeating until you are satisfied with the agent's performance.

***

#### <mark style="color:$primary;">**Testing Checklist**</mark>

<table><thead><tr><th width="172.00006103515625">Test</th><th width="447">What to Check</th><th>Passed?</th></tr></thead><tbody><tr><td>Greeting</td><td>Agent introduces itself and asks how to help</td><td>☐</td></tr><tr><td>FAQ accuracy</td><td>Agent answers known questions correctly</td><td>☐</td></tr><tr><td>Unknown questions</td><td>Agent does not make up answers</td><td>☐</td></tr><tr><td>Information collection</td><td>Agent asks for one detail at a time and confirms</td><td>☐</td></tr><tr><td>Forward to human</td><td>Agent transfers the call when asked</td><td>☐</td></tr><tr><td>Language switching</td><td>Agent responds in the customer's language</td><td>☐</td></tr><tr><td>Silence handling</td><td>Agent prompts the customer after a pause</td><td>☐</td></tr><tr><td>Interruptions</td><td>Agent handles mid-sentence interruptions</td><td>☐</td></tr><tr><td>Tool triggers</td><td>Correct tools fire at the right time</td><td>☐</td></tr></tbody></table>

***

#### <mark style="color:$primary;">**After Testing — Going Live**</mark>

Once you are satisfied with the test results:

1. Go back to the AI Agents list page.
2. Click Settings in the top bar.
3. Set this agent as the Default AI Agent if it is your primary agent.
4. Click Save Settings.

Your voice AI agent is now live and will handle incoming calls on your WhatsApp API number.

***

#### <mark style="color:$primary;">**Summary**</mark>

In this article, you learned how to test your voice AI agent by assigning it to your chat and making a real call, what scenarios to test (greeting, FAQs, unknown questions, information collection, human transfer, language switching, and edge cases), how to troubleshoot common issues, and how to take your agent live after testing.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://learn.doubletick.io/voice-ai-agent/how-to-test-your-voice-ai-agent.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.