Building a Basic AI Agent with the Agent Development Kit (ADK) and Claude
Press play on the video. It'll jump straight to the section that answers the
title above — no need to watch the full video.
A comprehensive guide to building your first AI Agent from scratch. Learn core ADK concepts like LLM Agent and Runner, then dive into Python code to create a 'birthday planner' agent and run it interactively from your terminal.
Core Concepts of the Agent Development Kit (ADK)
To build an agent with ADK, you need to understand several key components:
- **Agent**: Your application's core logic. ADK provides various agent types, the most fundamental being the 'LLM Agent'.
- **Tools**: These give your agent 'skills,' such as accessing external APIs or custom functions.
- **Runner**: The component that ties everything (agent, tools) together and manages interaction sessions.
- **Session**: Stores conversation history, allowing the agent to 'remember' previous interactions.
Claude Integration Options with ADK
There are two main ways to use Claude models with ADK:
1. **Via LiteLLM**: The standard method if you are already familiar with the LiteLLM ecosystem.
2. **Via LLM Registry Vertex**: A pre-built integration provided by the Vertex AI team. It offers a cleaner way to connect models to your agent, as shown in this tutorial.
More from Build & Deploy Autonomous AI Agents
View All
None
Lindy
Slack
Analyzing the Context Life Cycle in Agent Workflows with OpenAI Agents Python SDK
OpenAI Agents Python SDK
ChatGPT
Audit and batch update outdated content with Notion AI Agent
Notion AI Agent
Maintain Conversation History in n8n with Claude Code Session IDs
Claude
n8n
Customize agent branding and select AI model in Chatbase
Chatbase
ChatGPT
How to Build a Multi-Agent System Using ADK and MCP
Claude
Agent Development Kit (ADK)