Free AI resources

Lessons typed by humans.

Everything we’ve had to work out building AI systems for real clients, written down by hand, in plain language, free. No email gate. Chapters open; readings are one click each.

01 How to Map Out the Logic behind your AI System Almost every AI project that fails, fails the same way: someone wired a language model directly to a goal and hoped. This is how to design the thing properly, on paper, before you write a prompt. ~9 min read → 02 How to Give Better Prompts Most disappointing output is not a model failure. It is an underspecified request. Here is the difference between asking for something and specifying it. ~9 min read →

One entry per tool we actually run in production: what it's for, when we reach for it, and where it bites. Being written now.

Coming soon. The systems we run for clients, one per reading.

Coming soon. What actually happened on real projects, written up honestly.

01 Taste Skill, the anti-slop frontend pack The rules that stopped this site from looking like every other AI-built page. Written by Leonxlnx, free and open source. What each skill in the pack does, and how to install it. ~2 min read → 02 Emil Kowalski's skills, for motion that feels right The animation and interaction rules behind every hover, press and transition on this site. Written by Emil Kowalski of animations.dev. What each skill does and how to install them. ~1 min read → 03 Marketing Skills, for copy that sounds like a person The copywriting and editing rules behind the words on our services page. Written by Corey Haines, free and open source. What each skill does and how to install the library. ~1 min read → 04 HyperFrames, video from HTML, built for agents The open-source framework we use to turn HTML, CSS and GSAP into finished MP4s, and the 20 skills that teach an agent to run it. By HeyGen, Apache 2.0. ~2 min read → 05 The HyperFrames Student Kit, Nate Herk's editing pipeline The 14 skills that turn raw talking-head footage into a finished reel, cut, captioned and story-planned. By Nate Herk, MIT licensed. Our short-form scripts follow his structure. ~2 min read → 06 OpenWhispr, free local transcription The open-source dictation and transcription app whose Whisper engine we use to get word-level transcripts without sending audio anywhere. By the OpenWhispr team, MIT licensed. ~1 min read →