5 tracks. 40+ in-depth lessons. 30+ runnable agents. Every concept paired with a live demo you can fork. All free.
Start at Track 01 if you're new. Skip ahead if you've shipped with LLMs before — every track stands on its own.
Beginner
~3 hours
Start here if you've never built with LLMs. Every concept is explained twice: once like you're 10, once for the engineer in the room.
What's inside
Live templates included
Beginner → Intermediate
~4 hours
The seven canonical agentic patterns — wired up live. Tool use, RAG, planner-executor, reflection, routing, parallel fan-out, and HITL approvals.
What's inside
Live templates included
Intermediate
~3 hours
Turn natural language into safe SQL. AST validation, table allow-listing, schema-aware prompting, and the realities of running this in production (Uber QueryGPT-style).
What's inside
Live templates included
Intermediate → Advanced
~4 hours
When one agent isn't enough. Build researcher → writer → reviewer pipelines, peer-to-peer collaboration, A2A handoffs, and shared memory.
What's inside
Live templates included
Advanced
~3 hours
Production reality: traces, evals, ROI math, security, OpenAI-compatible gateways, multi-provider strategy. Real case studies from Klarna, Uber, Salesforce.
What's inside
Live templates included
We're adding new tracks every few weeks. Here's what's on deck — vote with your feedback on the contact page.
Episodic and semantic memory patterns, summarization buffers, vector recall — the building blocks for assistants that remember you across sessions.
A full track on prompt-injection defense, output validation with structured schemas, and red-teaming your own agents.
How to write golden datasets, score agent outputs automatically, and gate deployments on regression.
Multi-day guided projects: ship a customer-support agent, an internal data analyst, and a full RevOps swarm — end-to-end with case-study writeups.