# Getting Started

Not using Dot yet? [Sign up for free.](https://app.getdot.ai/register)

***

## 1. Connect Your Data

Go to **Settings → Connections** and add your data warehouse, semantic layer, or BI tool.

No code required—just permissions.

<figure><img src="/files/RnAUVSo1P4fE7jBExfKd" alt="Connect databases like Snowflake, BigQuery, Postgres, or semantic layers like dbt, Looker, and Power BI"><figcaption></figcaption></figure>

[See all integrations →](https://github.com/Snowboard-Software/snowboard_software/blob/main/dot/dot/integrations/README.md)

***

## 2. Describe What You Need

Open the **Context Agent** and tell it what you're trying to accomplish. It will interview you, explore your data, and set things up.

<figure><img src="/files/y4tAoSl3YZOaLA50znDM" alt="Context Agent interviewing a user about their product analytics use case"><figcaption></figcaption></figure>

You don't need to configure everything upfront—start with one use case and expand from there.

[Learn more about the Context Agent →](/train-dot/context-agent.md)

***

## 3. Start Asking Questions

Ask in plain English. Dot queries your data, visualizes results, and explains what it found.

You can ask questions directly in Dot, or connect Slack or Microsoft Teams so your whole team can get answers where they already work.

<figure><img src="/files/ulpi96XgUdEguRGYec2k" alt="Team members asking Dot questions in Slack and getting answers with charts"><figcaption></figcaption></figure>

[Set up Slack & Teams →](/integrations/slack-and-teams.md)

***

## What's Next

**Fine-tune how Dot understands my data**\
[Model →](/train-dot/model.md)

**Control who can access what**\
[Permissions →](/train-dot/permissions.md)

**Schedule recurring reports**\
[Scheduling →](/using-dot/scheduling.md)


---

# Agent Instructions: 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:

```
GET https://docs.getdot.ai/getting-started.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.