Blog Archive

Users ask similar questions in different words. Semantic caching with pgvector turns repeated intent into instant answers — no LLM call, no embedding, no retrieval pipeline.

Context windows fill up fast in long AI conversations. Sliding windows, progressive compression, and token budgeting — the patterns I built before I knew their names.

Vague instructions produce vague implementations. How I sit with the AI to refine rough ideas into concrete, implementable specs — before any code gets written.

The bottleneck isn't the AI — it's me. Three slash commands that form a loop: Plan, Work, QA. How structured phases replaced ad-hoc chatting and made AI development manageable.