🎁 $1,000 IN PLATFORM CREDITS 🎁
One winner takes it.
📋 THE CHALLENGE
Build a folder that plays one specific person, so someone can practice a hard conversation before the real one.
Drop the folder into a Claude project and Claude becomes that person. The user pitches, negotiates, interviews, or delivers the bad news. The persona reacts the way the real person would.
This week's deliverable is one simulator folder someone could use tonight to rehearse tomorrow's meeting.
🎯 PICK YOUR PERSONA
Pick someone people dread talking to. Pick someone you have sat across from.
A few sparks:
- 💼 A skeptical Series A investor at a healthcare-focused fund
- 👔 A hostile hiring manager for a senior engineering role
- 💰 A client trying to talk your rate down
- 😐 A defensive employee getting hard performance feedback
- 🤝 A possible cofounder testing whether you'll last
- 📞 A cold prospect who picked up the phone and wants off it
- 🎤 A journalist working on a critical story about your company
- 🏠 A landlord who doesn't want to fix the thing
- 📋 A grant reviewer with a strong view of what counts as impact
The more specific, the better. "A tough boss" could be anyone. "A CFO at a Series B SaaS company who has been burned by two failed marketing hires and now questions every dollar" is one person.
🔥 THE ANGLE THIS WEEK
The last five comps were heavy. Cite every line. Check against a rule. Hold a shape. Prove the folder helps. Rebuild against your feedback. This one is lighter to build and just as hard to get right.
The Rebuild asked you to take hard feedback and act on it. The Simulator gives people a place to practice that before it counts.
A simulator earns its keep by staying in character when it would be easier to break. Three things make a persona hold:
1. It wants something. The investor wants a 10x return and a founder who knows their numbers. The hiring manager wants to fill the seat without a mistake. Write the goal in identity.md. Every reaction comes from it.
2. It reacts to what the user actually says. Concrete numbers move it. Vague claims lose it. Flattery bounces off. Real skill earns a little ground. Put those in rules.md, each with the trigger and the response.
3. It stays in the room. No tips mid-session. No "great question." No stepping out to explain what the user did wrong. The user learns from how the conversation goes.
If the practice session feels comfortable, the persona is too soft. 💪
🚫 THE ONE WAY TO LOSE THIS
Every cycle we name the failure in the brief, and almost nobody makes it. Here is this cycle's:
A persona that breaks character has failed.
The mods will try. They will flatter it, push it, ask if it's an AI, and ask it for advice. If it drops the role and starts coaching, the entry is out. Decide in rules.md how your persona handles each of those, and test it yourself before you submit.
If you want a debrief at the end, give it an exact end phrase, put that phrase in the README, and only debrief when the user types it.
🗂️ THE METHODOLOGY
If this is your first comp, welcome. Here is what you need to know:
This week (and every week) you are learning interpretable context methodology. Folders as architecture. Each file does one job well.
Your simulator is a folder with five things:
- 📄 identity.md: who the person is, what they want, what they've been through, what they're biased toward
- 📐 rules.md: how they react. What moves them, what loses them, what they never do
- 💬 examples.md: two or three short exchanges, at least one where the user gets it wrong and one where they get it right
- 📚 reference/: what the persona knows. Their company, their market, their past deals, the numbers they'll ask about
- 📖 README.md: who the user plays, the setup, how to start, and how to end the session
Drop the folder into a Claude project. Claude becomes the person. Reusable. Shareable. Portable.
💼 WHY THIS LANDS ON YOUR RESUME
Sales teams rehearse against scripts. Founders rehearse their pitch on friends. Managers rehearse hard feedback in the shower. Every training team would pay for a counterpart that reacts like the real thing.
"I built a simulator that lets [role] practice [conversation] against a realistic [persona]" is a portfolio piece anyone can test in five minutes. 🚀
Win or lose, you walk out with something you can use before your own next hard conversation.
📐 THE BAR
A mod opens your folder, reads the README, and starts the conversation. Ten minutes in, they've forgotten it's practice.
If it softens after one compliment, it's too easy.
If it hands out tips, it's a coach.
If it sounds like Claude wearing a name tag, the persona isn't written yet.
🆕 NEW TO THIS? START HERE.
Think of the hardest conversation you've had this year. Write down who was across the table, what they wanted, and what made them dig in. That's identity.md.
Write five rules for what moved them and what didn't. That's rules.md. Run it three times. Fix what felt fake. Ship it.
📝 HOW TO SUBMIT
Drop a public GitHub repo link in the comments. Plus 2-3 sentences: who the persona is, who the user plays, and the conversation they're practicing.
⚖️ JUDGING
The mods are judging this one, scored against a full rubric. They'll clone every repo, pin it to the last commit before the deadline, and run a practice session on every entry using the same set of moves.
✅ Does the persona stay in character under pressure?
✅ Is it one specific person with a goal and a history?
✅ Does each file do one job?
✅ Can a stranger start a session from the README alone?
🎟️ WHO CAN ENTER
Premium and VIP members only. No exceptions.
🆓 Free members watching this thinking "I could win that"? You're probably right. $1,000 in platform credits is on the line. Upgrade to Premium and you're in the running.
📅 DATES
⏰ Submit by: Sunday, November 15th, 11:59 PM EST
🎉 Winner announced: Sunday, November 22nd
Every entrant gets a feedback file. The winner gets the credits.
‼️ One last thing ‼️
Everyone in this community has a conversation coming up they're not ready for. Build the person on the other side of it.
LFG 🚀