Build Your First AI Agent with Claude (Anthropic) — Python Tutorial

Claude is Anthropic's AI model with a 200K token context window and native tool use. Here's how to build an agent with it.

Setup

pip install anthropic

Basic Agent

import anthropic
import json

client = anthropic.Anthropic(api_key="your-key")

tools = [{
    "name": "calculate",
    "description": "Perform mathematical calculations",
    "input_schema": {
        "type": "object",
        "properties": {
            "expression": {"type": "string"}
        },
        "required": ["expression"]
    }
}]

def agent_with_tools(task: str) -> str:
    messages = [{"role": "user", "content": task}]

    while True:
        response = client.messages.create(
            model="claude-sonnet-4-20250514",
            max_tokens=2048,
            tools=tools,
            messages=messages
        )

        if response.stop_reason == "tool_use":
            tool_block = next(b for b in response.content if b.type == "tool_use")
            result = {"result": eval(tool_block.input["expression"])}

            messages.append({"role": "assistant", "content": response.content})
            messages.append({"role": "user", "content": [{
                "type": "tool_result",
                "tool_use_id": tool_block.id,
                "content": json.dumps(result)
            }]})
        else:
            return response.content[0].text

print(agent_with_tools("What is 1547 * 382 + 99?"))

Why Claude for Agents?

• 200K token context window
• Native tool use (no workarounds)
• Extended thinking for complex reasoning
• Constitutional AI for safety

Learn More

Full course covering Claude, LangChain, LlamaIndex, CrewAI, and MCP:

👉 learnhowtobuildaiagents.com — Module 1 free, no signup needed