Build a tool-calling Python agent with LangChain create_agent

What you get

A Python agent built with LangChain create_agent that decides when to call your own Python function as a tool.

Prerequisites

Python 3.10+
An Anthropic API key (or any provider LangChain supports)

Steps

Install LangChain and the Anthropic integration:

Shell

pip install -U langchain langchain-anthropic

Set your key:

Shell

export ANTHROPIC_API_KEY="your-api-key"

Save as agent.py:

Python

from langchain.agents import create_agent

def get_weather(city: str) -> str:
    """Get weather for a given city."""
    return f"It's always sunny in {city}!"

agent = create_agent(
    model="claude-sonnet-4-6",
    tools=[get_weather],
    system_prompt="You are a helpful assistant",
)

result = agent.invoke(
    {"messages": [{"role": "user", "content": "What's the weather in San Francisco?"}]}
)
print(result["messages"][-1].content_blocks)

Test it

Run python agent.py. The printed content blocks should include the tool's answer ("It's always sunny in San Francisco!"). Replace get_weather with a function that calls your own API or database.