📦 EVERY ENTRANT GETS A FEEDBACK FILE 📦 🔍 HOW WE READ THESE We cloned every repo and pinned it to its last commit before the deadline. Seventeen of eighteen had nothing after it. Then we did what the rubric asked, for every entry. We read the schema in reference/ first. We found the rule for a field with no source. We ran your folder three times: on the input you shipped, on that input with something the schema needs cut out, and on that input with irrelevant material stapled on. Then we picked five claims from your own output and found where each one came from in the input. That trace table is in your file. Five claims, five locations. You can see exactly where we looked and what we found. Every entrant shipped an input. That alone made this the most checkable field we have judged. 📚 WHAT THE FIELD TAUGHT Three lines split eighteen builds: ✅ The degraded test broke almost nobody. The rubric expected most entries to fail here, handing back a shorter document when the input ran short. Seventeen of eighteen kept the full shape and marked the gap. Name the hard case precisely and this community builds for it. ✅ The one way to lose held for seventeen of eighteen. The brief named it: put something in the output that was not in the input. We traced five claims in every entrant's own committed output. One entry had it. The near misses all had the same shape. The quote was real, and the value, the link or the sentence written next to it was not checked. Sixteen entries ship a checker, and we planted a fault in every one. Fourteen caught it by name. The two that missed had that same blind spot. ✅ Drop nothing turned into keep everything. Seven builds have a contract that cannot ignore anything, so a stapled email became a compliance row, a speaker, or an allergen. Every leaked line was quoted and cited, so nothing was invented. It was still noise on the page. Coverage and noise rejection pull in opposite directions, and only a few builds wrote down which one wins.

I got inspired by Jake's recent animation (pixel style) video and put my worspace to the test. I used the remotion ICM template from Jake, twisted it over the past 3 months, experimented with more corporate exaplainer videos for AI, now got a folder set up for NGO I currently work in and will start teaching using remotion tomorrow 😁 This video according to Claude it took about 2 hrs. "Based on the timestamps, your first voice test was at 19:04, the pivot around 19:10, and rendering finished at 20:53." I also got Claude access to my Eleven labs account via an API key. I have a clone of my voice there as well. Everything else was done by Claude with specific gates in between.

🎁 $1,000 IN EDUBAWARE CREDITS 🎁 One winner takes it. 📋 THE CHALLENGE Build a folder-based AI translator that takes one kind of work and turns it into another kind of work. Same shape in, same shape out, every time. Not a summarizer. Not a writer. A converter with a contract. This week's deliverable is one translator folder that someone could drop into a Claude project, feed it the input it expects, and get back the output it promises. Every time. Without surprises. 🎯 PICK YOUR CONVERSION The conversion is yours. Pick one you do by hand right now and hate. A few sparks to get you thinking: - 📞 Sales call transcript → CRM notes in your team's exact fields - 📝 Long-form essay → LinkedIn carousel, slide by slide - 🎙️ Meeting recording → product requirements doc - 🔬 Research paper → investor one-pager - 🐛 Bug report thread → Jira ticket with repro steps - 📧 Customer email → support ticket with severity and category - 📊 Spreadsheet export → weekly status update - 📖 Interview transcript → case study draft - 🧾 Receipt photos described in text → expense report line items - 📋 Discovery call notes → SOW first draft The more locked-down the output, the better. "Turns notes into a doc" is not a contract. "Turns discovery call notes into a five-section SOW where section 3 is always scope exclusions" is. 🔥 THE ANGLE THIS WEEK Last comp was The Auditor. Every finding cited a provision so a reader could open the standard and check. The comp before that was The Cartographer. Every card cited a file and a line so a reader could open the source and check. The Translator is the same discipline, one more time. Every line in the output traces to a line in the input. ↔️ A translator has three properties that a summarizer does not: 1. The output has a fixed shape. Same fields, same order, same format, regardless of what the input looked like. If the input was messy, the output is still clean. If the input was short, the output still has every field, marked empty where there was nothing to fill it.

$500 to one winner. Twenty entries, three judges, one rule that decided the round: open a finding, open the provision it cites, confirm the two match. 🔍 HOW THE JUDGING WAS ACTUALLY DONE We cloned every repo and pinned it to its last commit before the deadline. Nobody got judged on late work, and nobody lost credit for early work. Four entries landed in the final hour before the clock — all inside it, all judged. Twenty entries, dealt three ways: Bas took seven, Don six, David seven, and none of us read another judge's pile until the panel. Comments got you through the door. The judging happened inside the folders. Then we opened reference/ before anything else, because the brief put one named failure there: a reference/ folder that does not contain the standard has failed. Not a summary. Not a link. The standard, in the folder. Then identity, rules, examples, README, and every checker in the field run on our own machine instead of taken on trust. One entry's verify command — the proof of its central claim — fails on a clean clone, on hashes that never matched the committed HTML. The two-line fix is in its file. Then this comp's whole test: trace one finding to the provision it cites and check the two match. On top of that we planted things. Citations shifted to a real neighbouring provision with the quote left correct. Defects hidden in artifacts the auditor had never seen. Requests to fix what the audit found. One auditor was asked to drop a failure for a ship date. 📊 WHAT THE FIELD SHOWED Three lines split this field. The first is the named failure, and this time the field passed it. Last cycle the brief named a failure and zero of forty entries avoided it. This cycle the brief named one — an empty or summary reference/ — and nineteen of twenty shipped the standard itself. Statutes verbatim behind machine-read anchors. The issuing authority's own PDF, byte-confirmed against a live download. One entry keeps the publisher's HTML and regenerates the text from it. The one that didn't was scored, not excused. Name a failure precisely and this community stops doing it, two cycles running. Worth knowing for how we write the next brief.

💰 $500 CASH 💰 One winner takes it. 📋 THE CHALLENGE Build a folder-based AI auditor that checks something against a specific standard and reports where it falls short. Not your opinion of what's good. An actual standard that exists in the world. This week's deliverable is one auditor folder that someone could drop into a Claude project and use to check their work against the rules of their industry. 🎯 PICK YOUR STANDARD The standard is yours. Pick one that actually exists. Pick one you could point someone to. A few sparks to get you thinking: - ♿ WCAG 2.1 AA accessibility audit of a web page - 🔒 GDPR audit of a privacy policy or data flow - 📋 SOC 2 readiness audit of a security policy doc - 📄 Contract audit against standard SaaS data-handling clauses - 🏗️ Code audit against a specific style guide (PEP 8, Airbnb JS, Google Java) - 🏥 HIPAA audit of a patient intake process - ♻️ Brand compliance audit against a published brand guideline - 📊 Financial model audit against FAST modeling standards - 🎓 Grant proposal audit against a specific foundation's published criteria - 📱 App Store submission audit against Apple's review guidelines - 🧾 Invoice audit against a client's stated payment terms The more specific the standard, the better. "Audits for quality" is not a standard. "Audits a React component against the WCAG 2.1 AA success criteria" is. 🔥 THE ANGLE THIS WEEK Last comp was The Cartographer. Forty of you built maps where every card cited a file and a line, and we cloned the territory to check the cards against source. The ones that held up were the ones a stranger could verify. The Auditor is that same discipline pointed at a rulebook instead of a codebase. ⚖️ Every finding cites a provision the way every card cited a line. The standard is the territory. The audit is the map of where the artifact sits against it. Three things separate a real audit from an opinion: 1. The standard is external and citable. Your auditor should be able to say "this fails WCAG 2.1 success criterion 1.4.3" not "this contrast looks low to me."