> ## Documentation Index
> Fetch the complete documentation index at: https://docs.pavoai.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Self-serve

> Your team runs the Pavo improvement loop: build system knowledge, test approaches in parallel, ship what moves the metric.

**Designed for** teams with DS/ML bandwidth who want the tooling and want to run the improvement loop themselves.

## How the work happens

**System Knowledge**: Your team builds the knowledge book: the metric, why it matters, the business and product context, the data landscape, the warehouse tables. It self-updates and self-verifies from the actual work, so it doesn't go stale.

**Agent Studio**: Your team formulates hypotheses, generates *multiple* approaches to move the number, and tests them in parallel against a real benchmark.

## Who runs the loop

You.

## What stays yours

Code, data, and every learning. A per-client service account means nothing leaves your setup.

## Time to first win

Your cadence. Connect your sources, stand up a randomized holdout (even 2–3%), and ship.

## What you walk away with

A running improvement loop your team owns.

## How to start

<Steps>
  <Step title="Connect your sources">
    Wire up your data and tools, see [Connectors](/connectors/databricks).
  </Step>

  <Step title="Set the metric">
    Define the number you want to move and how it's measured.
  </Step>

  <Step title="Run a holdout">
    Stand up a randomized holdout so models train on clean data, then start shipping approaches.
  </Step>
</Steps>