> 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/grounded-trainer-mode.md).

# Grounded trainer mode

{% hint style="info" %}
This feature is being rolled out progressively. If the setting does not appear in your settings, contact **<support@meltingspot.io>**.
{% endhint %}

With **grounded trainer mode**, the AI Coach teaches. When a user asks a question, it first writes an answer in its own words, based on your Spot's content (and the documents and guidelines you have provided).

It then ends with one sentence pointing to **the** resource worth studying next, explaining why it is useful after this answer. This resource appears as a card the user can open.

Without this mode, the AI Coach mainly directs the user to relevant resources (👉 more information [here](https://help.meltingspot.io/english/coach-ai/user-experience/conversations-with-the-ai-coach.md)).

### Enabling grounded trainer mode

Go to **Settings > AI Coach**, **Persona** tab, **Proactivity** section, then turn on **Grounded trainer mode** (👉 more information [here](https://help.meltingspot.io/english/coach-ai/configuration/configuring-your-ai-coach.md)).

It is enabled by default as soon as the feature is available on your Spot.

{% hint style="warning" %}
Grounded trainer mode applies to conversations: **Two-way conversations** must be enabled for it to be useful.
{% endhint %}

### How its answers work

* **One recommended resource** at most per answer, never a list.
* If no resource is really relevant as a next step, the answer simply ends, without a forced recommendation.
* If your Spot's content does not cover the question, the AI Coach **does not invent**: it points to the closest resources (**3 at most**), or offers the fallback if one is configured.
* Answers are **short and structured** (paragraphs, lists, bold), with no tables and no links in the text: resources always appear as cards.
* The AI Coach addresses the user **formally**.
* It keeps the tone(s) chosen in **Persona**, and answers in the language of the user's message.
* While it searches, it shows which topic it is looking into.

### Documents provided by the admin

The AI Coach uses the documents and guidelines you have provided as its own knowledge. It does not mention "internal documents" to the user.


---

# 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/grounded-trainer-mode.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.
