🏆 WEEKLY COMP #12: THE AUDITOR 🏆

Matthew Creamer

11d (edited) • 💰 Competitions

💰 $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."

2. Findings are specific and located. Not "accessibility issues present." Instead: "the button at line 47 has a contrast ratio of 3.1:1, below the 4.5:1 minimum."

3. It reports pass and fail, not just fail. An audit tells you what you're compliant with too. That's what makes it an audit and not a complaint.

The auditor's opinion doesn't matter. The standard does. 💪

🚫 THE ONE WAY TO LOSE THIS

Last cycle we named a failure in the brief and zero of forty entries made it. So here's this cycle's:

A reference/ folder that does not contain the standard has failed.

Not a summary of the standard you wrote yourself. Not a link to it. The standard, or the relevant excerpt of it, in the folder, so a reader can open your finding, open the provision it cites, and check that the two match.

Twenty-nine Cartographer entries pointed at something a reader couldn't open. Don't repeat that here. If your standard isn't in reference/, nobody can verify your auditor, and an unverifiable auditor is an opinion generator.

🗂️ THE METHODOLOGY

If this is your first comp, welcome. Here's what you need to know:

This week (and every week) you're learning interpretable context methodology. Folders as architecture. Each file does one job well.

Your auditor is a folder with five things:

📄 identity.md (who the auditor is, what standard they enforce)
📐 rules.md (how they audit: what order, how they cite, how they classify severity)
💬 examples.md (2-3 example audits showing findings with citations)
📚 reference/ (the actual standard, or the relevant excerpts of it)
📖 README.md (how to use it, what to feed it)

Drop the folder into a Claude project. Claude becomes the auditor. Reusable. Shareable. Portable.

💼 WHY THIS LANDS ON YOUR RESUME

This is the most directly hireable thing we've built all year.

Compliance is a cost center every company hates paying for and can't avoid. Accessibility audits, security reviews, contract reviews, brand compliance. Someone is doing this work manually right now at every company you'd want to work for.

"I built an auditor that checks [artifact] against [standard]" is a portfolio piece you can walk into an interview with. It proves you understand a real standard AND can build systems around it. 🚀

Win or lose, you walk out with something you'd be proud to link from your LinkedIn.

📐 THE BAR

Feed your auditor something in its domain. It should tell you what passes, what fails, where exactly it fails, and which part of the standard it violates.

If it can't cite the standard, it's an opinion. If it only lists problems, it's a critique. If it maps what's there without judging it against a rule, that's last comp.

None of those are the assignment.

🆕 NEW TO THIS? START HERE.

You don't need to be a compliance expert to enter. Pick a standard you already work near.

Designer? Brand guidelines or WCAG. Developer? A style guide you already follow. Freelancer? Your own contract terms. Writer? A publication's submission guidelines. Anyone? Your company's expense policy.

The standard doesn't have to be famous. It has to be real and written down somewhere.

📝 HOW TO SUBMIT

Drop a public GitHub repo link in the comments. Plus 2-3 sentences on what your auditor checks and which standard it enforces.

⚖️ JUDGING

Jake, Matt, and the mods, scored against a full rubric. Same method as last cycle: we clone every repo, pin it to the last commit before the deadline, and try to break it.

✅ Does it audit against a real, citable standard? Or is it just an opinion?

✅ Are findings specific and located, with severity?

✅ Is the standard actually in reference/ where a reader can check it?

✅ README quality. Can a stranger figure this out?

🎟️ WHO CAN ENTER

Premium and VIP members only. No exceptions.

🆓 Free members watching this thinking "I could win that"? You're probably right. Premium is $325 for the year. The prize is $500. The math works in your favor on day one of being a paying member.

📅 DATES

⏰ Submit by: Friday, September 11th, 11:59 PM EST

🎉 Winner announced: Tuesday, September 15th

Every entrant gets a feedback file, not just the winner. Same as last cycle.

🚀 One last thing.

Editors improve work. Diagnosticians explain failure. Cartographers show you where things are. Auditors prove compliance.

Four different jobs. Same methodology. This one is the one somebody will pay you for.

LFG 🚀

57 comments

🏆 WEEKLY COMP #12: THE AUDITOR 🏆