> 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/what-is-coach-ai.md).

# What is Coach AI?

The AI Coach is MeltingSpot's conversational assistant. It appears directly in your software or website, in the form of a floating window. It offers training resources at the right moment, answers user questions, and guides them step by step through the product - without them needing to leave their interface to look for help.

{% hint style="warning" %}
The AI Coach is available on certain MeltingSpot plans only. If you don't have access to this feature, [contact us](mailto:support@meltingspot.io).
{% endhint %}

👀 The AI Coach is not available on mobile or tablet.

💡 You can rename your AI Coach from **Settings > AI Coach > Persona**, in the **Coach name** field. This documentation uses the generic term "AI Coach"; your users will see the name you've given it.

### **Key concepts**

**Playbook**: the website or application on which the AI Coach is integrated. You can have several playbooks (for example, a web app and a documentation site).

**Page**: a specific URL within a playbook. Targeting rules allow a single page to cover several similar URLs.

**Hotspot**: a visual anchor point on a page. It targets a specific interface element or applies to the entire page.

**Intent**: training content associated with a hotspot. It links the hotspot to a resource in your Spot (course, live session, document, forum...) and has a status: draft (not visible), published (active), or pending (created via the extension, not yet linked to content).

### **What the AI Coach does**

* Displays a training resource when hovering over a targeted element.
* Automatically triggers content when a user lands on a given page.
* Answers questions, guides step by step, and recommends resources, if two-way conversation is enabled.
* Proactively steps in to resume ongoing content or introduce a new resource.
* Redirects to a human (admin, channel, forum, external link) when it can't answer.

### **What the AI Coach does not do**

* It does not perform actions on behalf of the user.
* It does not make decisions for the user.
* It does not invent information.

### **Setting up the AI Coach**

1. A developer installs the AI Coach script on your site, via the **Deploy your coach** button (👉 more information [here](/english/coach-ai/set-up/installing-the-ai-coach.md)).
2. From the MeltingSpot extension, you place your pages, hotspots, and intents in point & click mode (👉 more information [here](/english/coach-ai/set-up/meltingspot-extension.md)).
3. From **Settings > Playbooks**, you manage your playbooks, pages, and intent content (👉 more information [here](/english/coach-ai/configuration/managing-your-playbooks.md)).
4. From **Settings > AI Coach**, you configure the conversational context — optional, a playbook works perfectly well without conversation enabled (👉 more information [here](/english/coach-ai/configuration/configuring-your-ai-coach.md)).
5. Create the content that will serve as the foundation for your Coach.

{% hint style="info" %}
💡 During your first visit to the Admin Dashboard, MeltingSpot's conversational assistant asks you a few questions to pre-fill this configuration (name, tone, project description...). You can find and edit this information from **Settings > AI Coach.**
{% endhint %}


---

# 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/what-is-coach-ai.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.