> For the complete documentation index, see [llms.txt](https://docs.umbraco.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.umbraco.com/umbraco-engage-ai/readme.md).

# Umbraco Engage AI

Umbraco Engage AI brings a marketing-focused Copilot into Umbraco Engage. A marketer can ask questions in plain language instead of navigating dashboards. Questions can cover campaigns, segments, goals, personas, traffic, and A/B tests, with the answer coming from the same data Engage already collects.

Umbraco Engage AI is **read-only**: it reports and explains, it never changes your Engage configuration or data.

{% hint style="info" %}
This is a beta feature. Expect rough edges as Umbraco Engage AI matures.
{% endhint %}

![The Copilot sidebar open in the Engage section, answering a campaign question](/files/AdeEVa9XAZx6adMy81oO)

## What it does

With Umbraco Engage AI installed, the Engage section is registered as Copilot-compatible, the same mechanism the Content and Media sections use. A set of Engage-specific tools becomes available to any agent granted access to them. See the full [Tools](/umbraco-engage-ai/getting-started/tools.md) reference for what each one answers.

## Key features

* **Plain-language marketing questions.** Skip the dashboard: ask things like "Which campaign is giving us the best return right now?"
* **Explains, not only reports.** Dedicated tools explain what a segment, goal, or persona means and how it's scored, rather than only naming what it is.
* **Works from either Copilot surface.** The same agent and tools answer from the Copilot sidebar and from Copilot Workspace. See [Asking Engage Questions](/umbraco-engage-ai/using-umbraco-engage-ai/asking-engage-questions.md).
* **Configurable, not fixed.** The agent's Instructions, AI Profile (model), and any attached Context resources shape tone and behavior. None of the answer format is hardcoded into Umbraco Engage AI itself.

## Packages

| Package                    | Purpose                                                                            |
| -------------------------- | ---------------------------------------------------------------------------------- |
| `Umbraco.AI.Agent.Startup` | Agent runtime, required to run any Copilot agent.                                  |
| `Umbraco.AI.Agent.Copilot` | The Copilot sidebar UI.                                                            |
| `Umbraco.Engage.AI`        | This package. Registers the Engage section for Copilot and ships the Engage tools. |

## Next steps

* [Installation](/umbraco-engage-ai/getting-started/installation.md). Install the packages and set up an agent.
* [Tools](/umbraco-engage-ai/getting-started/tools.md). The full list of tools and what each one answers.
* [Asking Engage Questions](/umbraco-engage-ai/using-umbraco-engage-ai/asking-engage-questions.md). Example prompts, from either Copilot surface.
* [Example: A Marketer Agent](/umbraco-engage-ai/using-umbraco-engage-ai/example-marketer-agent.md). Profile, instructions, context, and a guardrail, put together as one configuration to copy.


---

# 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.umbraco.com/umbraco-engage-ai/readme.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.