Category
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?
- ·3 min read
Rules That Agents Actually Follow: Enforcement Over Aspiration
A perfectly written CLAUDE.md cannot fix a contradictory codebase. The most effective rules file is short, opinionated, and backed by tooling.
- ·3 min read
A 3-Week Plan to Make Your Legacy React Codebase Agent-Ready
Three weeks, one engineer, one opinionated order. Stop the drift, collapse the duplicates, and let the rules you already have actually start working.
- ·3 min read
Why Your Legacy React Codebase Confuses AI Coding Agents
AI agents stumble on mature codebases because they have accreted multiple valid answers to the same question — and an agent has no way to know which one is current.
- ·3 min read
Building Model-Agnostic Workflows
The model you use today will not be the best model in 12 months. Write your workflow so that switching costs hours, not weeks.
- ·3 min read
Local Models: When You Run the Weights Yourself
Your code never leaves your machine. No API costs. No rate limits. The tradeoffs are real, but for the right use case, running local models is the right call.
- ·3 min read
GLM Models: The Open-Source Alternative from Zhipu AI
GLM-4 and CodeGeeX aren't widely discussed in Western developer circles. They should be. Open weights, strong multilingual coding, and a dedicated IDE extension that's genuinely good.
- ·3 min read
DeepSeek for Developers: Capable, Cheap, and Worth Knowing
DeepSeek-V3 matches Claude Sonnet on many coding benchmarks at roughly 10x lower API cost. Here's what it's actually good at, where it falls short, and what you need to know about data residency.
- ·3 min read
Claude Models Explained: Opus, Sonnet, Haiku for Coding
Opus for architecture, Sonnet for execution, Haiku for the fast repetitive stuff. And prompt caching that makes the pricing math work in your favour.
- ·3 min read
Token vs Subscription: Which AI Pricing Model Is Right for You
The break-even math is simpler than you think. Light users overpay on tokens. Heavy users overpay on subscriptions. Here's how to figure out which side you're on.
