> For the complete documentation index, see [llms.txt](https://help.meltingspot.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.meltingspot.io/english/coach-ai/configuration.md).

# Configuration

The AI Coach configuration is done from two places in your Spot's settings.

**Settings > Playbooks** is your management space: here you create your playbooks (one per site or application), manage pages and their targeting rules, view your hotspots and intents, and process pending intents. This is where you organize all of your AI Coach content.

**Settings > AI Coach** is your customization space: here you define your coach's identity (name, tone, topics to avoid), the context you give it to answer better (description of your project, audience, maturity level), and its behavior in case of uncertainty (fallback). These settings apply globally to all your playbooks, or specifically to a particular playbook.

Finally, the tool that connects the two: the MeltingSpot extension in point & click mode, which lets you create your hotspots and intents directly on your product's pages.

<table data-view="cards"><thead><tr><th></th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td><strong>Configuring the AI Coach</strong>: the coach's identity, context, and behavior.</td><td><a href="/english/coach-ai/configuration/configuring-your-ai-coach.md">Configuring your AI Coach</a></td></tr><tr><td><strong>Configuring the AI Coach's fallback</strong>: redirecting to a human when the coach can't answer.</td><td><a href="/english/coach-ai/configuration/configuring-the-ai-coachs-fallback.md">Configuring the AI Coach's fallback</a></td></tr><tr><td><strong>Managing your playbooks</strong>: creating and managing your playbooks.</td><td><a href="/english/coach-ai/configuration/managing-your-playbooks.md">Managing your playbooks</a></td></tr><tr><td><strong>Managing a playbook's pages</strong>: managing a playbook's pages and their targeting rules.</td><td><a href="/english/coach-ai/configuration/managing-a-playbooks-pages.md">Managing a playbook's pages</a></td></tr><tr><td><strong>Placing intents (point &#x26; click)</strong>: creating and editing hotspots and intents from the extension.</td><td><a href="/english/coach-ai/configuration/placing-intents-point-and-click.md">Placing intents (point &amp; click)</a></td></tr><tr><td><strong>Managing hotspots and intents</strong>: organize, publish, and process your intents from the settings.</td><td><a href="/english/coach-ai/configuration/managing-hotspots-and-intents.md">Managing hotspots and intents</a></td></tr><tr><td><strong>Preview as a member</strong>: test the AI Coach exactly as a specific member would see it.</td><td><a href="/english/coach-ai/configuration/preview-as-a-member.md">Preview as a member</a></td></tr></tbody></table>


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

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

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://help.meltingspot.io/english/coach-ai/configuration.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.