AI Agents: ReAct Loop and Autonomous Actions

A chatbot answers questions. An agent takes action: it calls tools, retrieves real data, and uses that data in its response.

Chatbot vs Agent

The ReAct Pattern

ReAct = Reasoning + Acting. An agent operates in a loop:

User question
       ↓
  REASON: Claude analyzes — is a tool needed?
       ↓
   ACT: Tool call (get_weather, read_file, ...)
       ↓
OBSERVE: We receive the tool result
       ↓
  REASON: Claude analyzes the result
       ↓
  (repeat until we have a final answer)
       ↓
 ANSWER: Final text response

A Simple Agent

import anthropic

client = anthropic.Anthropic()

TOOLS = [
    {
        "name": "get_time",
        "description": "Возвращает текущее время",
        "input_schema": {"type": "object", "properties": {}}
    }
]

def get_time() -> str:
    from datetime import datetime
    return datetime.now().strftime("%H:%M:%S")

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

    while True:
        response = client.messages.create(
            model="claude-sonnet-4-6",
            max_tokens=512,
            tools=TOOLS,
            messages=messages,
        )

        if response.stop_reason == "end_turn":
            return next(b.text for b in response.content if hasattr(b, "text"))

        messages.append({"role": "assistant", "content": response.content})
        results = []
        for block in response.content:
            if block.type == "tool_use":
                if block.name == "get_time":
                    result = get_time()
                results.append({
                    "type": "tool_result",
                    "tool_use_id": block.id,
                    "content": result
                })
        messages.append({"role": "user", "content": results})

print(run_agent("What time is it right now?"))

Common Agent Tools

• Web search — up-to-date information
• File reading — local documents
• HTTP requests — external APIs
• Code execution — computations
• Database — data storage and retrieval