Course · 8 chapters

Agent engineering

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.

Paidpractitioner8 chapters162 minEnglish + 6 languagesCertificate on completion

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

  1. 1
    Agent Engineering: parti da qui

    Un orientamento di 12 minuti allo skill path Agent Engineering da 7 capitoli — il capitolo di fondamenta, poi le primitive che ti servono prima di scegliere un archetipo di agent.

    12 min
  2. 2
    Il tuo primo agente AI

    Loop, tool, memoria — costruisci l'agente più piccolo possibile e scopri esattamente cosa lo fa funzionare.

    22 min
  3. 3
    Agentic Patterns

    Tool use, ReAct loop, orchestrazione multi-agent e guardrails per sistemi di agent affidabili.

    22 min
  4. 4
    Memoria e gestione dello stato degli agent

    Progetta sistemi di memoria che danno agli agent AI continuità, personalizzazione e la capacità di apprendere fra una sessione e l'altra.

    22 min
  5. 5
    MCP con Claude Code

    Collega Claude ai tuoi tool reali con il Model Context Protocol.

    18 min
  6. 6
    Padroneggiare le Agent Skills

    Costruisci pacchetti di istruzioni riusabili che insegnano agli agent AI i tuoi workflow — così insegni una volta e ne raccogli i benefici sempre.

    24 min
  7. 7
    RAG agentic

    Costruisci agent di retrieval che pianificano le query, routano fra le fonti e si autocorreggono — il pattern di architettura n. 1 nell'AI in produzione.

    20 min
  8. 8
    Failure e recovery degli agent

    Costruisci agent che sopravvivono ai fallimenti dei tool, ai loop fuori controllo e agli errori a cascata — con retry, circuit breaker ed escalation umana.

    22 min

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.