The reading list
Essays, tech notes, and the in-between.
- 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.
- AI·3 min read
design.md for an MUI Codebase: A Concrete Template
Part 4 was the meta-template. This is the full design.md for an MUI v6+ codebase — every token, variant, and rule, ready to copy.
- AI·3 min read
Session-Start Hooks That Pay for Themselves
Zero ongoing cost. Measurable improvement on every interaction. The underused feature of modern coding agents — what to put in it, and what not to.
- AI·3 min read
Writing Task-Specific Agent Prompts That Work First Try
If design.md is the agent's memory, task prompts are its muscle memory — the highest-leverage agentic asset you can build, and the most underused.
- AI·3 min read
What to Put in design.md: A Complete Template
A good design.md is a decision document, not a style guide. If a senior designer left tomorrow, would the next person make the same calls?
