> For the complete documentation index, see [llms.txt](https://docs.carto.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.carto.com/carto-user-manual/ai-agents/sharing-your-agent.md).
# Sharing your Agent
Once you've tested your AI Agent and are confident in its responses, you can make it available for others to use. To begin, you first need to activate the agent within the [Map settings for viewers](/carto-user-manual/maps/sharing-and-collaboration/map-settings-for-viewers.md) by enabling the AI Agent toggle.
You can use Preview Mode to interact with the agent exactly as an end-user would, providing a final opportunity to validate that the entire experience works as expected.
Viewers can chat with your agent on desktop, tablets and phones. On a phone, the agent opens full screen.
An AI Agent on a phone
After confirming everything looks good, you can share your map using CARTO's sharing options. This will make both the map and the integrated AI Agent available to your chosen audience, whether it's specific colleagues, your entire organization, or the public.
{% hint style="warning" %}
**Important: Public sharing limitations**
Agents with the [Query sources](/carto-user-manual/ai-agents/configuring-capabilities.md#query-sources-for-insights) capability can only be shared in Restricted or Organization mode and cannot be made public. This security restriction prevents unauthorized data access.
For public-facing applications:
* Build required logic into Workflows and expose them as MCP Tools.
* Use only pre-configured widgets and layers.
* Consider creating a separate, limited connection for public access.
{% 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://docs.carto.com/carto-user-manual/ai-agents/sharing-your-agent.md?ask=&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.
