> 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/user-experience/triggering-the-ai-coach.md).

# Triggering the AI Coach

The AI Coach applies automatic rules to prevent the same content from prompting the user endlessly. By default, this behavior is identical for all Spots. It can be customized intent by intent (👉 more information [here](https://help.meltingspot.io/english/coach-ai/configuration/managing-hotspots-and-intents.md#configuring-reappearance-conditions)).

{% hint style="info" %}
This article covers only hotspot-based triggering. For proactive interventions, more information [here](https://help.meltingspot.io/english/coach-ai/user-experience/proactive-messages.md).
{% endhint %}

### **The two states**

* **State A**, initial pop: the preview card is displayed. Light signal.
* **State B**, full content: the user has clicked and sees the full content. Strong engagement signal.

A user who closes it right at state A doesn't have the same level of interest as one who closes it after state B. The AI Coach takes this into account.

### **Auto-dismiss**

In state A, the window stays displayed for 30 seconds before closing automatically. Ten seconds before, a progress bar is displayed. Hovering over the window pauses the timer.

### **Muting rules**

When hovering over a hotspot, the AI Coach evaluates these rules in order. The first one that matches determines the behavior; otherwise, it pops normally in state A.

In all muting cases, a discreet icon (raised hand) signals the content without forcing it open. It disappears after 5 seconds. To bring it back, simply hover over the hotspot again.

**Rule 1: the content has already been completed** (courses, live sessions, learning paths only). The Coach no longer pops up offering the content but raises its hand. When clicked, the AI Coach asks if the user wants to review the content.

**Rule 2: the window was closed from state A less than a week ago** (by default). The Coach no longer pops up offering the content but raises its hand. When clicked, the AI Coach displays the content card.

**Rule 3: the user clicked the "Later" button from state A less than 24h ago** (by default). The Coach no longer pops up offering the content but raises its hand. When clicked, the AI Coach displays the content card.

**Rule 4: the window was closed from state B** (unlimited delay, by default). The Coach no longer pops up offering the content but raises its hand. When clicked, the AI Coach displays the content card.

{% hint style="info" %}
These rules never prevent access to the content: they simply avoid the window forcing itself on the user. The content remains accessible by hovering over the hotspot again.
{% endhint %}

The delays for rules 2 to 4 above are the default values. By default, there is also no repetition limit. To customize repetition and delays intent by intent, head to the Managing hotspots and intents page (👉 more information [here](https://help.meltingspot.io/english/coach-ai/configuration/managing-hotspots-and-intents.md#configuring-reappearance-conditions)).


---

# 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/user-experience/triggering-the-ai-coach.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.
