01
Move the how out of your prompts and into your codebase
Your prompt can't carry the burden of correctness alone. Strict types, lint rules, a design system, and deterministic checks do work a longer prompt never could.
Tagged ai-agents
All tags02
Using Grok Bot to keep my projects moving when I'm away from my desk
How I use Grok Bot as the go-between for my coding agents, so I can start work, check progress, and steer my side projects from anywhere.
03
React Native in an Industry That’s Changing
Shopify is moving from React Native to Swift / Kotlin. The article was interesting, and I highly recommend reading it. My takeaway is that agents change the dynamics around…
04
You don't need better agents, you need a better agent strategy
Escoffier's kitchens didn't necessarily have better cooks. Structure did the work. Same with agents: brigade beats prompting and hoping.
05
Pi: Learn once, keep your tools
Trying Pi as a daily driver so I'm not locked into any model, and I have more control over the tools I use every day.
06
Make your AI earn its keep: A grocery system that covers the subscription you're already paying for
A file-based meal and grocery system for LLMs. No code, no database — just markdown files, store circulars, and a weekly plan that can cover the subscription cost.
07
Steering coding agents, one small diff at a time
Want more control over the code an agent is writing? A Hunk-based workflow for reviewing small diffs before they become a large one.