What is an AI agent?

What is an AI Agent?

An AI agent is an autonomous system that uses an LLM as its "brain" to perceive its environment, reason about goals, and take actions — including using tools, making decisions, and completing multi-step tasks without constant human intervention.

Core Components

textCopy
┌─────────────────────────────────────────────┐
│                 AI Agent                    │
│                                             │
│  [Perception] → [LLM Brain] → [Action]     │
│       ↑                           ↓         │
│  [Memory/State] ←── [Feedback/Result]       │
└─────────────────────────────────────────────┘

Simple Agent Example

pythonCopy
from anthropic import Anthropic
import json

client = Anthropic()

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

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

    while True:
        response = client.messages.create(
            model="claude-opus-4-6",
            max_tokens=1024,
            tools=tools,
            messages=messages
        )

        if response.stop_reason == "end_turn":
            return response.content[0].text

        # Handle tool use
        if response.stop_reason == "tool_use":
            tool_result = execute_tool(response)
            messages.append({"role": "assistant", "content": response.content})
            messages.append({"role": "user", "content": tool_result})

Agent vs Simple LLM Call

Common Agent Patterns

Real-World Agent Use Cases

• Coding agent — reads files, writes code, runs tests, fixes bugs
• Research agent — searches web, summarizes, synthesizes findings
• Customer support agent — looks up account data, resolves issues
• Data analysis agent — queries databases, generates visualizations