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

# Dan

Meet Dan, DinMo's AI teammate, and learn how to turn customer questions into reviewed marketing actions.

Dan is your AI teammate in DinMo. Ask a question in plain language, explore your customer data, and move from an idea to a reviewed marketing action in one conversation.

Dan works with the data, business context, permissions, and tools available in your workspace. It explains what it found, prepares the next step, and waits for your approval before making a change.

<figure><img src="https://3204318043-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FxzBTp1t4OfqV67nXkVse%2Fuploads%2Fgit-blob-0456a882833f90ab1a2619e96f9757533a84809f%2Fask-dan-start-screen.jpg?alt=media" alt="Dan&#x27;s start screen with suggested starting points"><figcaption><p>Start with a useful question or describe the outcome you want to achieve.</p></figcaption></figure>

## Turn insight into action

Dan can help you:

* Understand customer behavior and explain what drives a result.
* Analyze audiences, campaigns, products, and marketing performance.
* Prepare segments, computed fields, and activations.
* Use predictions and recommendations available in DinMo.
* Explain how DinMo works and guide you through a task.
* Turn a business question into a concrete marketing plan.

Dan can combine these skills in one conversation. You can start with a question, refine the analysis, and ask Dan to prepare the audience or activation that follows from it.

## Give Dan the full picture

DinMo Context gives Dan the full picture of your business: who your customers are, what you have already done, and the rules every answer and action must follow.

Your customer data, activation history, definitions, and business guidance become one shared source of truth. Dan uses the relevant context automatically to understand your requests, produce consistent answers, and prepare actions that respect your rules.

You can also use **@** when you want to point Dan to a specific model, segment, definition, note, activation, or previous conversation. Dan shows which context informed its work, so you can review the basis of every important answer or action.

<figure><img src="https://3204318043-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FxzBTp1t4OfqV67nXkVse%2Fuploads%2Fgit-blob-1ffbd7866ae96cf57a0e17a253978d4e5eb5fc7a%2Fask-dan-question-with-context.jpg?alt=media" alt="Question for Dan with a relevant DinMo object attached as context"><figcaption><p>Give Dan an explicit object when it is central to the question.</p></figcaption></figure>

Learn how to build and govern this shared knowledge in [Context Manager](https://docs.dinmo.io/dan/context-layer.md).

## Stay in control

Dan follows your DinMo permissions. If you cannot access an object or perform an action, Dan cannot do it on your behalf.

Analyses include the available sources, context, calculations, and method. When Dan prepares a change, it presents a draft for review. Nothing is created, updated, or activated until you approve the proposed action.

A draft, a saved object, and a completed operation are different stages. Review the criteria, mappings, assumptions, and expected effect before confirming an action.

## Start with something useful

Before using Dan, a workspace administrator must activate it, accept the applicable AI terms, and give your role access.

To start:

1. In the DinMo navigation, click **Ask Dan**.
2. Describe the outcome you want.
3. Add the relevant workspace context with **@** when needed.
4. Review Dan's answer, sources, and method.
5. Ask a follow-up question or review the proposed action.

For example:

> Using @Customers and @Orders, explain why first-time buyers are not returning. Compare the last three complete months with the preceding three months, then prepare an audience of customers we should re-engage.

Be explicit about the population, period, metric, and exclusions when they matter. If a business term is ambiguous, Dan may ask for clarification or suggest a definition your team can reuse.

## Learn more

* [Context Manager](https://docs.dinmo.io/dan/context-layer.md): create shared definitions, rules, and notes.
* [Work with Dan](https://docs.dinmo.io/dan/working-with-dan.md): ask questions, review answers, and approve actions.
* [Administration and troubleshooting](https://docs.dinmo.io/dan/administration.md): manage access, SQL, sharing, usage, and support.


---

# 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.dinmo.io/dan/ask-dan.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.
