100 days. 100 projects. One LLM prompt at a time.
Each post here is a project built with AI assistance — browser extensions, bots, tools, dashboards, analyzers. Some took an afternoon. Some fought back. All of them taught me something about what these tools are actually good at, and where they fall short.
The rule: build something real, ship it, write about it honestly.
A Cloudflare Worker + KV URL shortener with a full admin UI, 37 slugs, and a branded linktree — plus everything that went wrong with DNS, redirect rules, and CNAME metadata before it worked.
A daily mindfulness check-in tool with breath, mind, and shift logging — Cloudflare Workers + D1. Now with anytime check-ins, public stats sharing, and a weekly Verbal Judo practice screen.
A gamified self-paced learning module covering AFL/AFL++ from first principles — edge coverage, the bitmap, mutation stages, adversarial critique, and a 30-day practice roadmap.
A privacy-first reader that strips trackers, follows redirects server-side, and hands you clean article text before any of that noise touches your browser.
One search box. Two social networks. A live stream of what the infosec community is talking about right now.
An interactive OWASP Top 10 vulnerability lab where you exploit real attack patterns and an AI tutor guides you through the why — without giving away the answer.
Blackout poetry from the Hacker News front page — an LLM picks the surviving words, the rest gets erased.
Notepad++ has a hidden easter egg — type the word 'random', select it, press F1, and a random quote appears. I extracted all 247 of them.
A single-file browser tool that queries MalwareBazaar, VirusTotal, OTX and more — then uses Gemini to generate a production-quality YARA rule with a condition-by-condition explanation.
A single-file Cloudflare Workers app that stress-tests any claim, URL, or article from every angle — steelman, strawman, synthesis.