All courses
Guided Course
evolvearchitectureops
Compound AI Systems
Multi-model routing, cascading, the classifier-generator-verifier triad, AI gateways, protocol composition, and the systems engineering that turns models into products.
0/13
13 lessons
- 1. Why One Model Isn't Enough5 min
- 2. The Classifier-Generator-Verifier Triad5 min
- 3. System Contracts and Component Design5 min
- 4. Routing Strategies5 min
- 5. Cascade and Fallback Patterns5 min
- 6. AI gateways in production5 min
- 7. Semantic caching5 min
- 8. Cost optimization at system scale5 min
- 9. Shadow testing and model evaluation6 min
- 10. MCP + A2A — the protocol stack8 min
- 11. Agent registries and capability discovery8 min
- 12. Observability for compound systems8 min
- 13. Capstone — building a compound AI system10 min
About Nybble™
The AI space moves fast.
Nybble™ is how you keep up — and stay sharp.
Snack
What happened. In two minutes.
The AI news cycle moves at a pace no one can keep up with. Snack distills what launched, what shipped, and what matters — every day, without the filler.
Go to SnackStack
The concepts behind the headlines.
News tells you what. Stack tells you why and how. From RAG architectures to agentic evals, these are the ideas that will shape what you build next.
Go to StackHack
Prove you actually get it.
Reading about LangChain is not the same as knowing it. Hack challenges you with production-grade questions, then shows you the references that make the answer stick.
Go to Hack