AI Agents
The complete agent engineering journey: agent loop, tool design, multi-agent systems, MCP, computer use, memory, production infrastructure, and evaluation. Pulls from the core AI Agents phase plus the full Agentic AI Engineering course.
The route
- AI Agents (foundation phase) — ML & AI Engineering (phase 07). 4 lessons covering the agent loop (think → act → observe), tool design with JSON Schema, state & memory, human approval gates, and agent evaluation.
- Agentic AI Engineering (full course) — Agentic AI Engineering. 10 phases, 51 lessons: advanced prompt engineering for agents, tool design, agentic RAG, multi-agent systems, MCP, computer use, memory systems, production infrastructure, and agent evaluation.
- Build Your First AI Agent from Scratch — Build Your First AI Agent from Scratch. A weekend project that takes you from zero to a working AI agent — the fastest way to get hands-on with agent concepts before diving deep.
What you build
Multiple production agent systems: a tool-using agent with error handling, a multi-agent orchestrated system, an MCP server, and a customer support agent with eval suites.
Every learning path
Create a free account — the opening phases of 24 of 30 courses are free, no credit card. Or see Pro pricing.
All courses · Pricing · About · FAQ · Glossary