> For the complete documentation index, see [llms.txt](https://docs.sprinthub.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.sprinthub.com/en/topics/artificial-intelligence/ai-agents/ai-agents-save-data.md).

# AI Agents - Save Data

## Setting the fields visible to the A.I.

The A.I. will have read permission for all fields listed in "**Lead Information**" in the Contextualization tab, that is, it will be able to use them during the conversation with the lead. It is essential that the fields it can edit are also available for reading.

<figure><img src="/files/c4f26914b468399f783c01d5a19571ce96b62d1b" alt=""><figcaption></figcaption></figure>

## Allowing field changes

To allow it to save data during the conversation, you must enable this feature as shown below, selecting the fields that can be changed.

If you want the agent to also be able to modify fields that are already filled in, you need to enable the option "**Allow data overwrite?**".

<figure><img src="/files/b9cbb7f8892178ccabfb430f8620b8f921d47d61" alt=""><figcaption><p><em>Agent edit screen.</em></p></figcaption></figure>

<figure><img src="/files/6852c1b841373d91be3550f891692be3abe2bed3" alt=""><figcaption><p><em>Selecting fields that can be changed.</em></p></figcaption></figure>

## Configuring rules to save the fields

It is important to make explicitly clear when the agent will be able to save the fields. Ideally, this should be done in the "Additional Rules" section. If you are working with custom lead fields, you can reference them by either alias or display name.

<figure><img src="/files/ddf4988f8707ec506da74f71ccc868f29c6a1b90" alt=""><figcaption><p><em>Additional Rules to change the fields.</em></p></figcaption></figure>


---

# 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 dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.sprinthub.com/en/topics/artificial-intelligence/ai-agents/ai-agents-save-data.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.