Beetl documentation
A lean data platform to enable data-driven teams with AI.
Beetl brings data in from the business systems you already run, keeps it as open tables in storage you own, and transforms it with SQL. You work with the result in the SQL editor, in chat, through scheduled automations, or from your own AI client over MCP.
New here? What Beetl is explains the model in one page, and the Quickstart gets you from an empty tenant to a query returning rows.
Getting Started
| Section | What it covers |
|---|---|
| Start Guide | What Beetl is, and how to get to a first answer. |
| Core concepts | The core nouns, each in a paragraph. |
Beetl Connect
| Section | What it covers |
|---|---|
| Connect your data | The ways data gets into Beetl: integrations, webhooks, files, and data read in place. |
| Build integrations | What a Connect package is, and how it reaches a tenant. |
Beetl Lakehouse
| Section | What it covers |
|---|---|
| Pipelines | Building, deploying and running pipelines, plus recipes for common cleanup steps. |
| Query and datasets | Asking questions of the data once it is in. |
| Dashboards and BI | Superset dashboards on your tenant data, opened inside Beetl. |
Work with AI
| Section | What it covers |
|---|---|
| Automations | Scheduled, observe-only checks on your data that return a finding, a report and the queries behind it. |
| Chat and the assistant | Where the assistant lives, what it knows, and how to work with it. |
| MCP and programmatic access | Connect Claude, Cursor or your own agent to Beetl over MCP. |
Trust and reference
| Section | What it covers |
|---|---|
| Security and compliance | The guarantees Beetl gives, where your data lives, and how it is deleted. |
| Troubleshooting | Common problems and how to fix them. |
| Reference | Limits and error codes, in one place. |
Documentation in progress
Some guides are still being written and are marked on their pages.