Course · 8 chapters
Engenharia de Agentes
Build production AI agents that use tools, remember across sessions, and recover from failures. Hands-on with MCP, Agent Skills, and agentic RAG, 8 chapters for engineers.
What you'll be able to do
- Build your first AI agent from scratch
- Apply ReAct loops and agentic patterns
- Design agent memory that persists
- Connect Claude to tools with MCP
- Ship agentic RAG that self-corrects
- Make agents resilient to failure
What's inside
- 1Agent Engineering: comece aqui
Uma orientação de 12 minutos para o skill path de Agent Engineering com 7 capítulos — o capítulo de fundamentos, depois as primitivas que você precisa antes de escolher um arquétipo de agent.
- 2Seu Primeiro Agente de IA
Loop, ferramenta, memória — construa o menor agente possível e veja exatamente o que faz ele funcionar.
- 3Agentic patterns
Tool use, loops ReAct, orquestração multi-agent e guardrails para sistemas de agents confiáveis.
- 4Memória e gerenciamento de estado em agents
Projete sistemas de memória que dão continuidade, personalização e aprendizado entre sessões aos seus agents.
- 5MCP com Claude Code
Conecte o Claude às suas ferramentas do mundo real usando o Model Context Protocol.
- 6Dominando as Agent Skills
Crie pacotes de instruções reutilizáveis que ensinam seus fluxos de trabalho aos agentes de IA — você ensina uma vez e colhe os frutos sempre.
- 7Agentic RAG
Construa agentes de recuperação que planejam consultas, roteiam entre fontes e se autocorrigem — o padrão de arquitetura nº 1 em IA de produção.
- 8Falhas e Recuperação de Agentes
Construa agentes que sobrevivem a falhas de ferramentas, loops descontrolados e erros em cascata — com retry, circuit breakers e escalação humana.
Frequently asked questions
- What will I learn in the Agent Engineering course?
- You learn to build production AI agents from the primitives up: tool use, memory and state, the Model Context Protocol (MCP), Agent Skills, agentic RAG, and failure recovery with retry and circuit breakers. It covers 8 chapters across roughly 2.7 hours.
- Who is this course for?
- It is built for software engineers and AI engineers at a practitioner level who want to design and ship reliable agent systems, not just prototypes. The path assumes you can read and write code.
- Do I need coding experience to take this course?
- Yes. This is an engineering-focused, practitioner-level path, so you should be comfortable with code and building software. It walks through hands-on agent construction rather than concepts alone.
- How long is the course and is there a certificate?
- The path has 8 chapters totaling about 162 minutes (roughly 2.7 hours). After you complete all chapters you earn a certificate from AI Academy by Anthropos.
- Is the Agent Engineering course free?
- No. Agent Engineering is a paid path included with an AI Academy by Anthropos subscription. It sits in the AI for Engineers track alongside other AI engineering content.
Earn a certificate
Complete all chapters to receive your certificate of completion.