Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.galileo.ai/llms.txt

Use this file to discover all available pages before exploring further.

Luna Studio Luna Studio 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 on the result, and lets you register the resulting metric back into the Galileo metrics store 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.
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, or contact us to get started.
Luna Studio projects page

What you can do

Fine-tune a custom Luna metric

Pick a metric template, supply a test set, generate a training set, and launch a training run — all in a guided flow.

Create synthetic data

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

Track training runs

Filter, star, and compare runs. See queued, training, fine-tuned, and registered runs in one view.

Register custom metrics

Once a new Luna metric is ready, register the resulting metric so it shows up across the Galileo platform.

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

Availability and deployment

How Luna Studio is provisioned for your org, and what’s fixed at deployment time.

Quickstart

The fastest path from sign up to a registered metric.

Core concepts

Projects, runs, metrics, test sets, training sets, and how they fit together.

Where to go next