Product area
Agents
Agent Framework and Agent Bricks: building, evaluating, and deploying agents on governed data.
Concepts
- 1Agents on DatabricksAn agent is a program that decides what to do. It takes a request, chooses which tools to call and in what order, reads the results, and produces an answer. The model does the choosing; everything else is ordinary software.Intermediate
- 2Agent tools as Unity Catalog functionsA tool is a function the model may decide to call in the middle of answering. On Databricks the durable place to keep one is Unity Catalog: you register a Python or SQL function, it gets a three-level name, an owner, a comment and grants, and from then on it…Advanced
- 3Evaluating agentsEvaluating an agent means running it against a set of representative inputs and scoring the outputs with scorers — some are LLM judges, some are plain code — instead of eyeballing transcripts. mlflow.genai.evaluate() is the entry point: give it an agent (or a…Advanced
- 4Agent memoryManaged agent memory gives an agent something to remember between conversations. You create a memory store — a workspace-scoped container, addressed by its displayname — and Databricks provisions the Lakebase storage behind it for you.Advanced Beta
- 5Agent Bricks: Knowledge Assistant and Supervisor AgentTwo builders you configure instead of code, both reached from Agents in the workspace sidebar, both producing an agent endpoint you can query from the AI Playground, from an app, or over the API.Intermediate
- 6Deploy an agent on Databricks AppsDatabricks documents one way to ship a custom agent: write it as an ordinary Python project, then run that project as a Databricks App. Two pieces are fixed and the rest is yours.Advanced
- 7Model Context Protocol on DatabricksThe Model Context Protocol is an open standard for connecting an agent to tools, resources and prompts. On Databricks it is the documented default way to give an agent capabilities, and a server comes from one of exactly three places:Advanced Preview
Also covered here
- Agent and MCP services as Unity Catalog securablesmodel services made an LLM endpoint a Unity Catalog object. The same idea now covers the two other things an agent is made of:
- Building a RAG pipelineRetrieval-augmented generation (RAG) is the pattern of fetching relevant material from your own data before asking a language model to answer, instead of relying only on what the model memorized during training. On Databricks that pipeline has six stages…
- Coding agents on Databricks, and how to keep them safeA coding agent — Claude Code, Cursor, GitHub Copilot, Codex — writes and runs code from a terminal or an editor. On its own it knows Databricks only as well as its training data does, which means old product names, flags that moved, and APIs that changed…
- Evaluation datasets for generative AIAn evaluation dataset is the fixed set of examples an application is scored against. Each record has inputs, a dictionary holding whatever the application takes (a question, a conversation, some context), and optionally expectations, a dictionary holding what…
- Human feedback on generative AI outputHuman feedback in MLflow is stored as an assessment attached to a trace, or to a single span inside one. There are two kinds, and the distinction runs through everything else on this page:
- MLflow Tracing for GenAI applicationsMLflow Tracing is the observability layer for generative AI code. One call into your application produces one trace: the record of everything that happened between the request arriving and the answer going out. A trace is a tree of spans, and a span is one…
- Production monitoring for GenAI appsProduction monitoring runs the scorers from agent evaluation against traffic instead of against a dataset. You take a scorer you already trust, register it against the MLflow experiment your app logs to, and start it with a sampling rate. From then on a…
- Prompt registryThe prompt registry stores a prompt template as an object in Unity Catalog instead of as a string in your source code. A prompt has a three-level name such as main.genai.supportsummary, immutable versions numbered automatically as you register new text…
- Using Genie outside the UI: API, embedding and agentsA Genie Agent is not tied to its own chat window. The same agent can answer from:
News
Resources
Author an agent and deploy it on Databricks AppsDocumentation · Databricks · checked 24 Oct 2026Free
Create agent tools using Unity Catalog functionsDocumentation · Databricks · checked 24 Oct 2026Free
Create agent tools using Unity Catalog functionsDocumentation · Databricks · checked 10 Oct 2026Free
Nothing of that kind for this area. Try the full list.