Agent Engineering

AI agent engineering course, how to build AI agents, Model Context Protocol tutorial, MCP with Claude Code, agentic RAG, ReAct agent pattern, AI agent memory and state, multi-agent orchestration, agent failure recovery, AI engineering course for developers

practitioner

en

• Build a minimal AI agent with one model, one tool, and one memory slot
• Apply agentic patterns: tool use, ReAct loops, and multi-agent orchestration
• Design agent memory and state that persists across sessions
• Connect Claude to your tools using the Model Context Protocol (MCP)
• Build reusable Agent Skills that teach agents your workflows
• Build agentic RAG that plans, retrieves, self-corrects, and routes across sources
• Make agents resilient with retry, circuit breakers, and human escalation

• Url: https://aiacademy.anthropos.work/chapters/agent-engineering-intro/ · Agent Engineering: Start Here · Position: 1 · A 12-minute orientation to the Agent Engineering skill path — primitives for tool use, memory, skills, retrieval, and failure recovery
• Url: https://aiacademy.anthropos.work/chapters/your-first-ai-agent/ · Your First AI Agent · Position: 2 · Build the smallest possible agent — one model, one tool, one memory slot — and see exactly what makes the loop tick
• Url: https://aiacademy.anthropos.work/chapters/agentic-patterns/ · Agentic Patterns · Position: 3 · Tool use, ReAct loops, multi-agent orchestration, and guardrails for reliable agent systems
• Url: https://aiacademy.anthropos.work/chapters/agent-memory/ · Agent Memory & State · Position: 4 · Design memory systems that give AI agents continuity across sessions
• Url: https://aiacademy.anthropos.work/chapters/mcp-with-claude/ · MCP with Claude Code · Position: 5 · Connect Claude to your tools using the Model Context Protocol
• Url: https://aiacademy.anthropos.work/chapters/mastering-agent-skills/ · Mastering Agent Skills · Position: 6 · Master the art and science of building Agent Skills — reusable instruction packages that teach AI agents your workflows
• Url: https://aiacademy.anthropos.work/chapters/agentic-rag/ · Agentic RAG · Position: 7 · Build agents that plan, retrieve, self-correct, and route across knowledge sources
• Url: https://aiacademy.anthropos.work/chapters/agent-failure-recovery/ · Agent Failure & Recovery · Position: 8 · Build agents that survive tool failures, runaway loops, and cascading errors — with retry, circuit breakers, and human escalation

• Build a minimal AI agent with one model, one tool, and one memory slot
• Apply agentic patterns: tool use, ReAct loops, and multi-agent orchestration
• Design agent memory and state that persists across sessions
• Connect Claude to your tools using the Model Context Protocol (MCP)
• Build reusable Agent Skills that teach agents your workflows
• Build agentic RAG that plans, retrieves, self-corrects, and routes across sources
• Make agents resilient with retry, circuit breakers, and human escalation

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.

Course Mode: online · Course Workload: PT162M · Mode: online