Archive
A slow-moving archive of notes on AI systems, product patterns, and engineering decisions worth revisiting.
2026
- 03-08Early March AI signal: less talk about model size, more talk about workflow closure
- 02-26Which LLM evaluation metrics actually help product decisions
- 02-14Seven operational questions I ask before a RAG system goes live
- 01-30After the agent framework hype, what capabilities actually remain
- 01-12Small models matter again, and not just because they are cheaper
2025
- 12-18Turning prompts from inspiration into maintainable assets
- 11-27Why search-shaped AI products keep turning into information workbenches
- 10-21How I keep an AI reading list without being dragged around by every new term
- 09-11Bigger context windows make application design more disciplined, not less
- 08-19From demo to delivery, the missing piece is often responsibility, not model quality
- 07-06Why a heavier AI tool stack often calls for a simpler personal workflow