Chat with LLMs and prototype AI apps using AI Playground

Legacy

Building agents in AI Playground is a legacy approach. To build and test agents, use the Agent Bricks CLI and run your agent locally with agentbricks dev. To query models from code, see Query foundation and embedding models.

The AI Playground is a chat environment for Large Language Models (LLMs). In the playground, you can interactively test, prompt, and compare LLMs, as well as prototype tool-calling agents and question-answering bots.

Requirements

• Your Databricks workspace must be in a region that supports Foundation Models. See Model serving features availability.
• Models called in AI Playground may be subject to license requirements and use policies. See Applicable model terms.

note

If Playground is not available in your workspace, reach out to your Databricks account team for more information.

Use AI Playground

To use the AI Playground:

1. Select Playground from the left navigation pane under AI/ML.
2. Select the model you want to interact with using the dropdown list on top.
3. You can do either of the following:
   1. Type in your question or prompt.
   2. Select a sample AI instruction from those listed in the window.
4. You can select the + to add an endpoint. Doing so allows you to compare multiple model responses side-by-side.

Prototype AI agents in AI Playground

You can also get started building AI agents in AI Playground. For more information, see Get started: Query LLMs and prototype agents with no code.