Course · 8 chapters
Agent Engineering
Agent primitives — tool use, memory, skills, MCP, retrieval, and failure recovery
What you'll be able to do
- A 12-minute orientation to the 7-chapter Agent Engineering skill path — the foundations chapter, then the primitives you need before you pick an agent archetype.
- Loop, tool, memory — build the smallest possible agent and see exactly what makes it tick.
- Tool use, ReAct loops, multi-agent orchestration, and guardrails for reliable agent systems.
- Design memory systems that give AI agents continuity, personalization, and the ability to learn across sessions.
- Connect Claude to your real-world tools using the Model Context Protocol.
- Build reusable instruction packages that teach AI agents your workflows — so you teach once and benefit every time.
What's inside
- 1Agent Engineering: Start Here
A 12-minute orientation to the 7-chapter Agent Engineering skill path — the foundations chapter, then the primitives you need before you pick an agent archetype.
- 2Your First AI Agent
Loop, tool, memory — build the smallest possible agent and see exactly what makes it tick.
- 3Agentic Patterns
Tool use, ReAct loops, multi-agent orchestration, and guardrails for reliable agent systems.
- 4Agent Memory & State Management
Design memory systems that give AI agents continuity, personalization, and the ability to learn across sessions.
- 5MCP with Claude Code
Connect Claude to your real-world tools using the Model Context Protocol.
- 6Mastering Agent Skills
Build reusable instruction packages that teach AI agents your workflows — so you teach once and benefit every time.
- 7Agentic RAG
Build retrieval agents that plan queries, route across sources, and self-correct — the #1 architecture pattern in production AI.
- 8Agent Failure & Recovery
Build agents that survive tool failures, runaway loops, and cascading errors — with retry, circuit breakers, and human escalation.
Earn a certificate
Complete all chapters to receive your certificate of completion.