AI Agent Design Patterns — ReAct, Multi-Agent Systems

AI Agents are LLM-powered systems that take sequences of actions to accomplish goals, rather than responding to a single prompt. An agent perceives its environment through tool outputs, reasons about what to do next, takes actions (tool calls), and iterates until the task is complete. The key difference from a plain LLM call: agents have a feedback loop — outputs inform the next input.

The ReAct (Reasoning + Acting) pattern is the most widely used agent architecture:

Loop: while not done:

1. LLM receives: [system prompt] + [conversation history] + [available tools as JSON schema]
2. LLM outputs either: a. Tool call: {"name": "search", "input": {"query": "..."}} b. Final answer: direct text response (task complete)
3. If tool call: execute tool → append result to history → go to 1
4. If final answer: return to user

Context management is critical: each loop iteration adds messages to context. A complex task might require 20 iterations × 500 tokens = 10K tokens before answering. With GPT-4 at $10/1M input tokens, a complex agent task costs $0.10 just in context re-reading.

Multi-agent patterns: orchestrator agents delegate to specialized sub-agents. Example: ResearchAgent calls WebSearchAgent and DataAnalysisAgent in parallel, then synthesizes results. LangGraph and CrewAI implement graph-based multi-agent coordination.

import anthropic
client = anthropic.Anthropic()

tools = [{"name": "search_web", "description": "Search the web",
    "input_schema": {"type": "object", "properties":
        {"query": {"type": "string"}}, "required": ["query"]}}]

messages = [{"role": "user", "content": "What is the current price of Claude API?"}]

while True:
    response = client.messages.create(model="claude-opus-4-5",
        max_tokens=1024, tools=tools, messages=messages)
    if response.stop_reason == "end_turn":
        print(response.content[0].text)
        break
    for block in response.content:
        if block.type == "tool_use":
            result = search_web(**block.input)
            messages.append({"role": "assistant", "content": response.content})
            messages.append({"role": "user", "content":
                [{"type": "tool_result", "tool_use_id": block.id, "content": result}]})