Agentic AI Engineer
Build agents that plan, call tools, and get things done.
LLM APIs, RAG, tool calling, agent frameworks (LangGraph, CrewAI, Claude Agent SDK), MCP, and evaluation — the core build path for engineers shipping agents.
9 lessons · about 3.2 hours
Certificate of completion
Earn your Agentic AI Engineer certificate
Verified edition
Mark every lesson in this course complete. You have finished 0 of 9. 9 to go.
See a sample certificate. Anyone can check a certificate with its code at /verify. It records course completion. It is not an exam or an accredited qualification.
Tokens, context windows, chat templates and sampling — the four things every agent engineer needs to understand correctly before anything else in this path makes sense.
Writing prompts that produce reliable, parseable output every time — not just good chat replies.
Defining tools, handling the request/response loop, and common failure modes.
Getting the right context to the model without blowing the token budget.
LangGraph, CrewAI, smolagents and the Claude Agent SDK — what each is actually for.
The Model Context Protocol, and why it replaced bespoke tool integrations.
Keeping an agent coherent across long-running, multi-turn tasks.
Building an eval set, catching regressions, and debugging a broken agent loop.
Shipping an agent for real, and a capstone project to prove you can.