I'm shutting this place down. Not because it failed. Not because I lost interest. Just moving the courses behind a proper paywall and building something more sustainable. But here's the thing about promises: I made one to the 30 or so of you who joined early. Lifetime access means lifetime access. That doesn't change just because the website does. So if you want the latest version of Co-Write OS—which I just finished overhauling into something genuinely better than what's sitting in the Classroom right now—you'll get it free on my new site. We're talking completely rewritten modules, tighter frameworks, and the actual system I use now instead of the version I was still figuring out six months ago. No catch. No "but actually you need to pay the difference." You're in. Period. But only if you speak up. I'm not chasing anyone down for this. What I need from you: Drop a comment below if you want access to the updated course. I'll personally get you set up on the new platform. If you're not interested (or you've moved on to other things—no judgment), I'd still recommend going through what's in the Classroom while you can. It's all still there. For now. That's it. No dramatic farewell speech. No "this community changed my life" monologue. It's been good. You've been good. Now go write something worth reading. —Nick

You know that thing where you ask AI to "write in your voice" and it produces something that technically uses words you might use but sounds like a corporate LinkedIn influencer possessed your keyboard? That's not an AI problem. That's a you problem. (I say this with love. And maybe three drinks. Mostly love.) AI can't follow patterns you haven't documented. When you say "write like me," AI has nothing to work with. So it guesses. Badly. Same structures, same rhythms, same soul-sucking monotony it uses for everyone else. The written equivalent of beige paint. The fix isn't better prompts. It's better inputs. Enter: The Tempo Extraction Exercise Tempo is one of four layers in VAST (Vocabulary, Architecture, Stance, Tempo). It's the most tangible. The layer where you can literally count patterns instead of gesturing vaguely at "vibes" like you're describing a coffee shop's aesthetic. I published the full exercise on Substack, but here's the actionable version for those of you who actually do the work. (All twelve of you. I see you.) THE EXERCISE (20 minutes, 3 parts) Part 1: Sentence Length Distribution (7 min) Grab 3 pieces of your writing. 500+ words each. Count sentences in each bucket: Short: 1-7 words Medium: 8-18 words Long: 19+ words Calculate your rough ratio across all three samples. Mine: 35% short, 50% medium, 15% long. This ratio tells AI what rhythm to target. Without it? Monotonous medium-length sentences that put readers to sleep. (AI defaults to medium the way middle managers default to "let's circle back.") Part 2: Sentence Starters (6 min) List the first word of every sentence in your samples. Look for repetition. Common patterns: 🧉 "I" = first-person dominant 🧉 "But/And/So" = conjunction starters (conversational energy) 🧉 "The" = noun-leading, content-focused 🧉 Verbs = command/imperative style Your top 3-4 starters are your defaults. Document them. Mine lean heavy on conjunction starters. "But" and "And" everywhere. English teachers hate me. Readers don't seem to mind.

Hi. I want to learn more about using AI to write novels.

I need to tell you something about this community. It's not an accident that it exists. It's not a "lead magnet" or a "top of funnel play" or whatever the growth hackers are calling it this week. It's a bet. I spent five years posting on X. Under 100 followers. Five years of playing the algorithm game exactly how you're supposed to play it. And I finally figured out why it wasn't working: the game changed and nobody sent me the memo. Here's the short version: The ROI of algorithm-chasing has collapsed. Not for consuming content (TikTok still works great for melting your brain). But for building anything sustainable as a creator? The slot machine is broken. Meanwhile, the ROI of trust networks is exploding. Discord. Paid Substacks. Communities like this one. We're in what I'm calling Phase 2 of the Content Reformation. The skepticism phase. People are actively retreating from public platforms into private spaces where trust can actually be verified. By Phase 3 (2026-2027), the drawbridge goes up. The people inside trust networks become the gatekeepers. Everyone else gets stuck in the algorithmic wasteland fighting for scraps. This community is my lifeboat. And yours. I'm building here because I believe the relationships we form now—before the retreat accelerates—are the ones that matter in three years. So: introduce yourself if you haven't. Start a conversation. Help someone. The people in this room are going to be your referral network when word-of-mouth becomes the only discovery that works. The drawbridge is still down. But it's going up. Let's make sure we're all inside when it does. What's your read on this? Am I being dramatic, or does this match what you're seeing too?

Alright, confession time. I've been using AI collaboration ass-backwards for months. Maybe you have too. Here's what I was doing: 🧉 Use AI for brainstorming 🧉 Use AI for drafting 🧉 Use AI for generating variations 🧉 Edit alone, exhausted, at midnight See the problem? All my AI collaboration was expansion—more ideas, more words, more options. Then I'd do contraction alone. The cutting. The tightening. The "what is this piece actually about" reckoning. At night. Tired. When my judgment was sharp as a spoon. The insight that changed everything: When AI expands your content, its voice creeps in. More words = more chances for generic phrasing. When AI contracts your content, your voice survives. Because you wrote the original—AI just identifies which of your words are strongest. More AI involvement in contraction = more authentic output. (I know. Sounds backwards. Felt backwards. Then I tried it and my editing time dropped 40%.) The rhythm that actually works: Expand → Contract → Expand → Contract 1. Generate ideas (with AI) 2. Pick one direction (with AI) ← most people skip this 3. Draft it out (with AI) 4. Cut to essential (with AI) ← and this Prompts that hit hard: "Cut 40% while keeping everything that matters. Tell me what you removed and why." "Read this as a skeptical reader one boring paragraph from closing the tab. What would you skip?" "Which sentences could be in anyone's article? Which sound like no one else would write them?" That "tell me why" is doing heavy lifting. Forces judgment, not just mechanical reduction. I put together a full toolkit on this: 25 contraction prompts organized by phase—finding the core, cutting with judgment, choosing between options, tightening. Plus checkpoint questions so you stop expanding forever and actually ship. Download: The Contraction Prompts Worksheet → https://sendfox.com/lp/m52jjn Discussion question: What's your ratio of expansion to contraction when you're working with AI? Be honest. Are you doing the hard part alone?