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: Hier starten

    Eine 12-minütige Orientierung zum 7-Kapitel-Skill-Path Agent Engineering – das Grundlagenkapitel, dann die Primitives, die du brauchst, bevor du einen Agent-Archetyp wählst.

    12 min
  2. 2
    Dein erster KI-Agent

    Loop, Tool, Memory — baue den kleinstmöglichen Agenten und sieh genau, was ihn antreibt.

    22 min
  3. 3
    Agentic Patterns

    Tool Use, ReAct-Schleifen, Multi-Agent-Orchestrierung und Guardrails für zuverlässige Agentensysteme.

    22 min
  4. 4
    Agent Memory & State Management

    Entwirf Memory-Systeme, die KI-Agenten Kontinuität, Personalisierung und die Fähigkeit geben, sitzungsübergreifend zu lernen.

    22 min
  5. 5
    MCP mit Claude Code

    Verbinde Claude mit deinen realen Tools über das Model Context Protocol.

    18 min
  6. 6
    Agent Skills meistern

    Erstelle wiederverwendbare Instruktionspakete, die KI-Agenten deine Workflows beibringen — damit du einmal lehrst und jedes Mal davon profitierst.

    24 min
  7. 7
    Agentic RAG

    Baue Retrieval-Agenten, die Abfragen planen, zwischen Quellen routen und sich selbst korrigieren — das #1-Architekturmuster in produktiver KI.

    20 min
  8. 8
    Agent-Fehler & Wiederherstellung

    Baue Agents, die Tool-Ausfälle, unkontrollierte Schleifen und kaskadierende Fehler überleben — mit Retry, Circuit Breakern und menschlicher Eskalation.

    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.