> ## Documentation Index
> Fetch the complete documentation index at: https://docs.teamfollowup.ai/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> Use the public API base URL: https://api.teamfollowup.ai/api.
> Authenticate public API requests with Authorization: Bearer YOUR_API_KEY.
> Use product-owned terms: agents, campaigns, projects (GoHighLevel sub-accounts), contacts, calls, outcomes, skills, cadences, phone numbers.
> Scope requests by locationId rather than projectName.
> Read the guide linked from each API reference group before recommending an endpoint.

# Test your agent

> Try calls, texts and follow-up actions before using the agent with leads.

Use the test panel beside your agent to check the version you have saved.
Wait for saving and setup to finish before judging the result.

## Test a call

Start a test call from the **Call** view. When the agent calls you in the browser,
answer the ringing call. Answering from Chat switches you to the Call view.
Speak as a lead would and check that the agent asks the right questions.

## Test Chat

When Chat is enabled, open **Chat** and send a message. Try a normal question,
a correction and a request for an action. You can also text during a call to
check that the conversation stays connected across both channels.

## Continue or start over

Ending a call does not erase the conversation. Continue by text or start another
call in the same conversation to check that known answers are remembered.

Use **Start over** when you want a genuinely fresh test. It resets the call and
chat conversation together. Simply switching between Call and Chat is not a reset.

## Check more than the reply

Review the action results as well as the wording. Try missing information, no
available appointment times, an unanswered transfer and a request to stop contact.
Also leave a call silent to check your [Call handling](/agents/tfu-live-call-handling) settings.

Test actions use simulated effects where supported. A successful browser test
helps you judge the conversation, but you still need a connected number and
correct integration settings for real delivery.

Refine [Instructions](/agents/tfu-live-brain), [Conversation Style](/agents/tfu-live-voice)
or [Workflows](/agents/tfu-live-capabilities), then repeat the same test.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.