Rudder Lookout
Private Beta
Learn about Rudder Lookout, how it works, and what you can do with it.
Rudder Lookout is currently in Private Beta, where we work with early users and customers to test new capabilities and gather feedback before making it generally available.
Contact your Customer Success Manager if you are interested in enabling Lookout for your team.
Rudder Lookout is an AI-powered analytics and activation agent for marketing teams. You ask questions in plain language, and an AI agent answers them and acts on them against the customer data you already trust — without writing any SQL, raising a ticket, or waiting on an analyst.
Each result that Lookout shares is saved as a durable artifact you can revisit and share, rather than a transient chat reply.
What Lookout connects to
Lookout works with the systems you connect it to, for example:
- When you link your warehouse, it answers questions on your data
- When you connect RudderStack to read your sources, destinations, and audiences already created in your workspace
The following integrations are currently supported:
| System | What it unlocks |
|---|
| Warehouses | Run read-only queries against PostgreSQL, Snowflake, Redshift, BigQuery, and Databricks |
| GitHub / GitLab | Explore repositories, review pull and merge requests, and propose changes as pull/merge requests |
| RudderStack | Read sources, destinations, transformations, Tracking Plans, and audiences — and, with a read-write connection, manage them |
| Slack | Answer questions from a direct message or a bound channel |
| External AI tools | Let approved external AI tools call a curated set of Lookout’s tools |
Features like building and activating audiences using Lookout are coming soon.
What Lookout produces
Lookout’s output is a set of durable artifacts:
- Answers: Charts and tables produced from a live warehouse query
- Dashboards: Saved, parameterized views that re-run their queries on every load
- Documentation: Generated descriptions of how your events are instrumented, stored in the Context Hub
- Measurement plans: Structured definitions of tracking changes
- Pull requests: Code changes proposed against your repositories
How it works
Lookout reasons over the context a RudderStack team already has. This includes the events flowing through your pipelines, the Tracking Plans that define them, the warehouse they land in, and the repositories where they are instrumented. Because of this, a single conversation can move from a warehouse metric, to the Tracking Plan definition behind it, to the instrumentation code that emits it.
Two rules govern how the agent operates:
- Least privilege, per task: The agent is given only the tools a task requires. With nothing connected, it can converse but has no external reach — connect a warehouse and it can query it, connect a repo and it can review it, and nothing more.
- A human approves consequential actions: The agent prepares the work and a person pulls the trigger — code changes arrive as pull or merge requests for review, dashboards and documents are drafts you approve, and public sharing is always an explicit human choice.
Next steps
Questions? We're here to help.
Join the RudderStack Slack community or email us for support
