> ls ./notes/*.md
Notes work as a research log: brief context, problem, approach, conclusion and next step. This is not blogging for blogging, but traces from lab experiments.
# RAG pipeline without magic
How I assemble a retrieval layer: sources, chunking, pgvector, eval sets, tracing and honest quality checks.# AI Factory task planning loop
How a planner should work: goal, decomposition, skill selection, checkpoints, execution trace and manual approval for risky actions.# Context mining for large codebases
How to extract not just files from a repository, but a useful context pack: entrypoints, dependencies, risk zones and decision history.# Prompt evals before prompt vibes
Why prompts should be versioned like code: cases, expected behavior, regression checks, tone constraints and safe answer boundaries.# MoonShine AI workflows for content ops
How to add AI to an admin panel carefully: drafts, translations, content blocks, preview and control before publishing.# Frontend systems that survive real users
Notes on complex interfaces: design tokens, state, SSR, performance and accessibility without unnecessary magic.# Backend under load starts with boring questions
Patterns for APIs, queues and data: when a monolith is faster and where event-driven loops become necessary.