Introduction to the Databricks AI cookbook

The Databricks AI cookbook and its sample code take you from a proof-of-concept (POC) to a high-quality production-ready application using Mosaic AI Agent Evaluation and Mosaic AI Agent Framework on the Databricks platform.

The Databricks Generative AI Cookbook is a definitive how-to guide for building high-quality generative AI applications. High-quality applications are:

  • Accurate: They provide correct responses

  • Safe: They do not deliver harmful or insecure responses

  • Governed: They respect data permissions & access controls and track lineage

Developed in partnership with Mosaic AI’s research team, this cookbook lays out best-practice development workflow from Databricks for building high-quality RAG apps: evaluation-driven development. It outlines the most relevant ways to increase RAG application quality and provides a comprehensive repository of sample code implementing those techniques.


There are a few ways you can build a rag app using this cookbook:

The Databricks approach to quality

Databricks takes the following approach to AI quality:

  • Fast, code-first developer loop to rapidly iterate on quality.

  • Make it easy to collect human feedback.

  • Provide a framework for rapid and reliable measurement of app quality.

Animated walkthrough of the Mosaic AI review app in Databricks.

This cookbook is intended for use with the Databricks platform. Specifically:

  • Mosaic AI Agent Framework that provides a fast developer workflow with enterprise-ready LLMops & governance.

  • Mosaic AI Agent Evaluation that provides reliable, quality measurement using proprietary AI-assisted LLM judges to measure quality metrics that are powered by human feedback collected through an intuitive web-based chat UI.

Code-based workflows

Choose the workflow below that most meets your needs:

Time required

What you’ll build


10 minutes

Sample RAG app deployed to web-based chat app that collects feedback

Rag demo

2 hours

POC RAG app with your data deployed to a chat UI that can collect feedback from your business stakeholders

Build and deploy a POC

1 hour

Comprehensive quality, cost, and latency evaluation of your POC app