Building with LLMs
Hurricane Signal
Field notes on the real things we're building with LLMs across our projects — what worked, what broke, and what we learned. Practical, occasional, no hype.
Get the next issue
One email when there's something genuinely useful to share. No schedule to pad, no filler. Unsubscribe in one click.
We store your email address with our email provider (Resend) for the sole purpose of sending you Hurricane Signal. We never sell or share it, and every email includes a one-click unsubscribe. Questions about your data? Get in touch.
A taste of what you'll get
We built a Lighthouse skill that's not allowed to break the stack
We built a Claude Code skill that audits any site with Google Lighthouse and produces a fix plan with one hard rule: it must never change how the project renders. The pattern of treating your architecture as a machine-checkable invariant is the bit you can steal.
Turn any website into a branded promo video — from just a URL
We built a tool that watches a web app the way a person would, then produces a narrated, on-brand promo video from nothing but a URL — and the whole thing was built, and debugged, by an AI coding agent that could see its own video output.
Your Claude Code transcripts know what your next skill should be — mine them
We extracted 1,451 of our own prompts from Claude Code's session logs and counted what we kept retyping. The repeats became three new skills and a pile of instructions the agent now reads automatically.
