Product Manager

3 courses · ~8 hours· 1 certification available

phase 1 — How models actually work

Understand why engineers say 'the model can't do that' and how to evaluate vendor claims.

[ ] Understanding Transformers [preview]

When your engineers say 'the model can't do that,' you'll understand why. When a vendor says 'our model handles 200K tokens,' you'll know to ask harder questions.

2 sections · 4 lessons

[ ] Attention Mechanisms (3 lessons)
[ ] Embeddings (1 lesson)

[→ start course]

phase 2 — How AI takes action

Learn the mechanism behind every AI feature on your roadmap.

[ ] Understanding Tool Calling

Tool calling is the mechanism behind every AI feature on your roadmap — chatbots, auto-complete, data extraction. Understanding it helps you write better specs and set realistic expectations.

4 sections · 10 lessons

[ ] Foundations (2 lessons)
[ ] How Models Decide (2 lessons)
[ ] Advanced Patterns (3 lessons)
[ ] Security and Production (3 lessons)

[→ start course]

phase 3 — Context limits and real capabilities

Learn what context window sizes actually mean for your users.

[ ] Context Engineering

The 'marketing vs. reality' section was practically written for product decisions. Learn what context window sizes actually mean for your users.

8 sections · 25 lessons

[ ] Tokens and Inference (2 lessons)
[ ] The Real Size of Your Context Window (4 lessons)
[ ] Anatomy of the Messages Array (5 lessons)
[ ] Dynamic Allocation: Tool Calling (2 lessons)
[ ] The Ralph Wiggum Loop (3 lessons)
[ ] Sub-Agents: Managed Runtimes for AI (3 lessons)
[ ] Message Passing: The Erlang OTP of AI (3 lessons)
[ ] Context Management Strategies (3 lessons)

certification: Certified Context Engineer

[→ start course]

key terms

Transformer·Context Window·Tool Calling·Context Engineering·Agent·Prompt Injection