Skip to content
estudIA
ES

6 guides

AI agents

Agents are models that use tools in a loop to reach a goal. These guides explain how they work, where they shine and where they fail.

  1. Featured

    4 min read

    What Is an AI Agent? Chatbots vs Assistants vs Agents

    What makes an AI agent different from a chatbot or an assistant, how the agent loop works, coding and browser agents, and when an agent is worth using.

    Read the guide →

  2. 4 min read

    AI Agent Design Patterns: From Workflows to Multi-Agent

    The building blocks of agentic systems explained: prompt chaining, routing, parallelization, orchestrator-workers, evaluator-optimizer, agents and multi-agent.

  3. 3 min read

    Coding Agents Compared: Claude Code, Codex and Cursor

    What a coding agent is, how Claude Code, Codex and Cursor work, what they cost and which to choose, with tips for using them safely.

  4. 4 min read

    Your First Agent With the Claude API, Step by Step

    Build a simple tool-using agent in Python: how tools are defined, how the agent loop works and how to add limits and human approval.

  5. 3 min read

    AI Agent Safety: Permissions, Injection and Oversight

    The real risks of giving an AI agent tools and permissions (prompt injection, excessive autonomy, data leaks) and the concrete measures to prevent them.

  6. 2 min read

    Agents That Use the Browser and the Computer

    How agents that browse and operate software for you work (Claude in Chrome, the Agents API, Muse), what they're good for and what precautions to take.