The reading list
Essays, tech notes, and the in-between.
- AI·3 min read
How I Actually Wrote This Site's design.md
Parts 4–9 were the templates. This is the living artifact — a section-by-section tour of the design.md that powers this site, the calls I made, the rules that stuck, and the lines I would write differently if I started over.
- AI·3 min read
The Agent-Ready Audit: A Runnable Checklist for Any React Codebase
One bash script, six numbers, an opinion about each. Run it on Monday morning and you have a prioritised list of what to fix before agents can help.
- technical-notes·3 min read
The question generator, the cron job, and shipping it locally
Grounded question generation is one prompt away. Wrap the project with a local cron, a one-line backup, and a popular-guests landing query — and the podcast index runs on its own.
- technical-notes·3 min read
The React side: guest pages, search UI, and codegen'd types
A Vite + React SPA with three real pages — popular guests, guest detail, search — wired to FastAPI through codegen'd TypeScript types from a shared Pydantic schema. No UI framework, three pages, type-safe end to end.
- AI·3 min read
MIGRATIONS.md Recipes: Six Concrete Stack-Pair Migrations
Part 2 said write a MIGRATIONS.md. This post is six concrete recipes — one per common stack pair — that any agent can execute end-to-end.
- AI·3 min read
design.md for a Tailwind + shadcn/ui Codebase
Utility-first codebases need a design.md more, not less. Without one, agents reach for every utility class in the bundle. Here is the full file.
- technical-notes·3 min read
Search without embeddings: Postgres tsvector, LLM rerank, and 30-second clips
For a few hundred podcast episodes, Postgres full-text search plus an LLM rerank beats embedding-based RAG on both quality and operational simplicity. No vector DB, no embedding pipeline.
- AI·3 min read
design.md for a Chakra UI v3 Codebase: Recipes, Tokens, Rules
Chakra v3 changed the game with recipes and semantic tokens. Here is the complete design.md that takes advantage of both — copy, swap your brand, ship.
- technical-notes·3 min read
Building a provider-switching LLM client: one interface, three providers, task-tier routing
A small adapter package lets you swap Anthropic, OpenAI, and local Ollama via an env var, route cheap classification to Haiku and synthesis to Opus, and add prompt caching without touching call sites.
- AI·3 min read
The Quiet Platform Shift: Why Orchestration Layers Like Multica and Paperclip Matter More Than the Next Model
Every conversation about AI in software has quietly moved one altitude up. The interesting question is no longer which model — it's what runs above them. A survey of agent orchestration platforms, from Multica and Paperclip to CrewAI, LangGraph, MetaGPT and ChatDev, and a light forecast of where this is heading.
