Skip to main content
Agents are AI-powered entities that can understand and respond to messages. Each agent is backed by an LLM provider and can be customized with roles, goals, instructions, and additional features like memory, tools, and RAG.

Quick Start

Agent Lifecycle

  1. Create: Use studio.create_agent() to create an agent with a name, provider, and configuration
  2. Configure: Add features like memory, tools, contexts, or RAI policies
  3. Run: Execute the agent with agent.run() to get responses
  4. Manage: Update, clone, or delete agents as needed

Key Features

Provider Selection

Choose from multiple LLM providers:

Streaming Responses

Get real-time responses:

Structured Outputs

Get type-safe responses with Pydantic:

Memory

Maintain conversation context:

Knowledge Bases (RAG)

Add document retrieval:

Tools

Execute Python functions:

RAI Guardrails

Add safety features:

Agent Properties

Next Steps

Creating Agents

Learn all agent creation options

Running Agents

Execute agents and handle responses

Managing Agents

Update, clone, and delete agents

Agent Features

Add memory, tools, and more