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.
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: begin hier
Een oriëntatie van 12 minuten op het Agent Engineering-leerpad van 7 hoofdstukken — eerst het basishoofdstuk, daarna de bouwstenen die je nodig hebt voordat je een agent-archetype kiest.
- 2Je eerste AI-agent
Loop, tool, geheugen — bouw de kleinst mogelijke agent en zie precies wat hem laat werken.
- 3Agentic patterns
Tool use, ReAct-loops, multi-agent-orkestratie en guardrails voor betrouwbare agentsystemen.
- 4Agentgeheugen en statusbeheer
Ontwerp geheugensystemen die AI-agents continuïteit, personalisatie en het vermogen geven om over sessies heen te leren.
- 5MCP met Claude Code
Verbind Claude met je real-world tools via het Model Context Protocol.
- 6Agent Skills Beheersen
Bouw herbruikbare instructiepakketten die AI agents jouw workflows leren — zodat je één keer uitlegt en er elke keer profijt van hebt.
- 7Agentic RAG
Bouw retrieval-agents die queries plannen, over bronnen routeren en zichzelf corrigeren — het #1 architectuurpatroon in productie-AI.
- 8Falende agents en herstel
Bouw agents die toolfouten, op hol geslagen loops en cascaderende fouten overleven — met retries, circuit breakers en menselijke escalatie.
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.