What is an AI Agent?

An AI agent is a system where a language model doesn’t just generate text — it takes actions. The model reasons about a goal, decides which tools to invoke, executes them, observes results, and loops until the task is done.

Tool-Calling Explained

You describe tools (functions) to the model as JSON schemas. The model outputs structured calls; your code executes them and returns results back into the conversation context.

// 1. Define a tool
const tools = [{
  name: "search_web",
  description: "Search the internet for up-to-date info",
  input_schema: {
    type: "object",
    properties: { query: { type: "string" } },
    required: ["query"]
  }
}];

// 2. Pass tools to the model
const response = await anthropic.messages.create({
  model: "claude-sonnet-4-6",
  tools,
  messages: [{ role: "user", content: userGoal }]
});

The Agentic Loop

• 1

  Send the user message + tool definitions to the LLM.

• 2

  If the model responds with stop_reason: "tool_use", extract the tool call.

• 3

  Execute the tool in your environment (API call, DB query, code run…).

• 4

  Append the tool result as a tool_result message.

• 5

  Repeat until stop_reason: "end_turn" — the agent is done.

while (true) {
  const res = await anthropic.messages.create({ messages });
  if (res.stop_reason === "end_turn") break;

  for (const block of res.content) {
    if (block.type === "tool_use") {
      const result = await executeTool(block.name, block.input);
      messages.push(assistantMsg, toolResultMsg(block.id, result));
    }
  }
}

Common Agent Tools