Nybble™
All courses

Guided Course

evolvearchitecturecode

Loop Engineering and Agent Harnesses

Harness design, context management, subagent orchestration, evaluation-as-steering, and the Claude Agent SDK — the infrastructure layer that makes agents reliable.

0/14
Start course
14 lessons
  1. 1. What Is a Harness8 min
  2. 2. The Inner Agentic Loop8 min
  3. 3. Context Management at Scale9 min
  4. 4. Turn-Based and Goal-Based Loops11 min
  5. 5. Time-based and proactive loops8 min
  6. 6. Evaluation-driven iteration8 min
  7. 7. Subagent architecture8 min
  8. 8. Dynamic workflows and fan-out8 min
  9. 9. State persistence and session management8 min
  10. 10. Circuit Breakers and Safety6 min
  11. 11. Building with the Claude Agent SDK5 min
  12. 12. Custom Harness from Scratch5 min
  13. 13. Harness Evaluation and Optimization6 min
  14. 14. Capstone — a Loop-Engineered Agent8 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 Snack
Stack

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 Stack
Hack

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