AI Engineering from Scratch: first-principles guide to the agent loop and context budgeting
ghumare64 · x · 2026-11-18
The 'AI Engineering from Scratch' project released illustrated field notes teaching AI engineering from first principles: build the smallest version you can explain. Lesson 1 covers the agent loop (DECIDE → ACT → OBSERVE, feed tool results into the next decision, cap steps/time/cost); Lesson 2 frames context as a budget—classify info into goal/rules/evidence/tool results and keep only what the next step needs, retrieving, trimming and refreshing as the task evolves.
More from coding & agent
- GPT-6.2 Sol and Astra spotted live in OpenAI Codex, official release post pending — mark_k · 2026-11-18
- swyx after a week with Devin Bots: multi-agent teams that own outcomes, not tasks — marvinvonhagen · 2026-11-18
- Vivek Haldar: hundreds of tiny enterprise tools are now cheaper to vibe-code than to maintain — vivekhaldar · 2026-11-18
- Adaption ships as a Hermes Agent plugin for in-agent custom model training — sarahookr · 2026-11-18
- Agent security testing thread: capture evidence before deleting the dependency graph — krishnan · 2026-11-18
- Throwaway analysis environments: agents should leave reproducible evidence, no running servers — krishnan · 2026-11-18