> ## Documentation Index
> Fetch the complete documentation index at: https://v2galileo-feat-update-docs-main-26464861746.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Welcome to Luna Studio

> Create custom Luna metrics and deploy them to Galileo

<img className="block dark:hidden h-10 my-6" src="https://mintcdn.com/v2galileo-feat-update-docs-main-26464861746/Yk5eDVpmigwjsk0t/images/luna-studio/logo/light.svg?fit=max&auto=format&n=Yk5eDVpmigwjsk0t&q=85&s=a02f59cecf37935f61d4bbbe6abc1add" alt="Luna Studio" noZoom width="268" height="48" data-path="images/luna-studio/logo/light.svg" />

<img className="hidden dark:block h-10 my-6" src="https://mintcdn.com/v2galileo-feat-update-docs-main-26464861746/Yk5eDVpmigwjsk0t/images/luna-studio/logo/dark.svg?fit=max&auto=format&n=Yk5eDVpmigwjsk0t&q=85&s=0208cd9f348e612b35684c127c484df5" alt="Luna Studio" noZoom width="268" height="48" data-path="images/luna-studio/logo/dark.svg" />

Luna Studio is Galileo's latest innovation and the first in the world for building real-time **custom evaluation metrics** tuned to your AI Agent. You bring a small labelled test set; Luna Studio generates a training set from it, fine-tunes a [Luna metric](/concepts/luna/luna) on the result, and lets you register the resulting metric back into the [Galileo metrics store](/concepts/metrics/overview) for use in evaluation, observability, and guardrails.

If you've ever wanted a metric that understands *your* definition of "tone consistent", "grounded answer", or "policy-violating output" — without writing a custom evaluator from scratch — Luna Studio is built for that.

<Note>
  **Enterprise tier and your own deployment.** Luna Studio is part of the
  enterprise tier of Galileo and is deployed by Galileo into your own cluster
  or cloud. See [Availability and deployment](/luna-studio/availability), or
  [contact us](https://galileo.ai/contact-sales) to get started.
</Note>

<Frame caption="The Projects page — your home base in Luna Studio">
  <img src="https://mintcdn.com/v2galileo-feat-update-docs-main-26464861746/Yk5eDVpmigwjsk0t/images/luna-studio/projects/projects-home.png?fit=max&auto=format&n=Yk5eDVpmigwjsk0t&q=85&s=7a951134d11b64eb889a22fc00055c4b" alt="Luna Studio projects page" width="1024" height="639" data-path="images/luna-studio/projects/projects-home.png" />
</Frame>

## What you can do

<CardGroup cols={2}>
  <Card title="Fine-tune a custom Luna metric" icon="sparkles" href="/luna-studio/quickstart">
    Pick a metric template, supply a test set, generate a training set, and launch a training run — all in a guided flow.
  </Card>

  <Card title="Create synthetic data" icon="database" href="/luna-studio/datasets/overview">
    Upload a small test set (300 samples) as CSV/JSONL files, fetch from URLs, or import directly from Galileo. Use Luna Studio to upsample that data to 1000s
  </Card>

  <Card title="Track training runs" icon="chart-line" href="/luna-studio/projects/training-runs-home">
    Filter, star, and compare runs. See queued, training, fine-tuned, and registered runs in one view.
  </Card>

  <Card title="Register custom metrics" icon="circle-check" href="/luna-studio/runs/register-metric">
    Once a new Luna metric is ready, register the resulting metric so it shows up across the Galileo platform.
  </Card>
</CardGroup>

## Who Luna Studio is for

* **ML and AI engineers** who need evaluation metrics tailored to a specific domain (legal, healthcare, RAG over internal docs, multilingual support, etc.).
* **Applied scientists** who want to skip the boilerplate of fine-tuning evaluator models.
* **Platform teams** standardizing how their org evaluates LLM applications across many products.

## Start here

<CardGroup cols={2}>
  <Card title="Availability and deployment" icon="building" href="/luna-studio/availability">
    How Luna Studio is provisioned for your org, and what's fixed at deployment time.
  </Card>

  <Card title="Quickstart" icon="rocket" href="/luna-studio/quickstart">
    The fastest path from sign up to a registered metric.
  </Card>

  <Card title="Core concepts" icon="book-open" href="/luna-studio/core-concepts">
    Projects, runs, metrics, test sets, training sets, and how they fit together.
  </Card>
</CardGroup>

## Where to go next

* New to evaluation metrics? Read [Core concepts](/luna-studio/core-concepts).
* Already have a Galileo account? Jump to the [Quickstart](/luna-studio/quickstart).
* Wondering which platforms we support? See [Integrations overview](/luna-studio/integrations/overview).
* Stuck? Check the [FAQ](/luna-studio/reference/faq) and [Troubleshooting](/luna-studio/reference/troubleshooting).