Hey everyone, I'm Josh I'm 19, based in the UK, and I build AI automation and outbound systems for business owners. I've already shipped a few real things: a contactless payment platform for schools that's live, different process automations for German Businesses, and I'm the technical cofounder of a data startup that just got full approval. And I'm building my agency around AI, automation & consulting, sold globally through a personal brand. Why I'm here: I do my best work around people who are actually building, and I've been doing this mostly solo. I want to fix that. So I'm looking to connect with one or two people who are also building something serious. Whether that's an accountability partner to keep each other on track daily, or just someone in the same trenches to swap wins, losses, and ideas with. Deffo not looking for motivation that dies in three days, looking for someone consistent who's in it for real. If that's you, or you're just building in AI and want to talk, comment or reach out. Glad to be here.

First, I have to say it: Nate's video genuinely blew my mind. The roast skill changed the way I make decisions, and the whole "stop letting the model agree with you" idea is gold. If you haven't run it yet, do — it's that good. As I adapted it to my own workflow, I noticed two small additions that pushed it even further for me. Funny enough, they're the exact same two things that leveled up my multi-LLM council a while back: a second pass, and more than one brain. Tweak 1 — a second round (cross-examination). Round 1 stays exactly like Nate's: the six personas attack independently and score the idea. Then I added a round 2 where the personas look at each other's takes and pressure-test them: - Expansionist → Contrarian: is that "fatal flaw" really fatal, or are we over-worrying it? - Contrarian → Expansionist: is that upside actually reachable with the resources we have, or is it wishful? - Deep-researcher → everyone: flag any claim with no evidence behind it (anything unverified loses weight). - Buyer → everyone: does the real customer even care about this, or is it just an internal debate? - First-principles → everyone: separate solid logic from hope, and keep anyone from quietly redefining the product. Each persona revises its score after the pressure, and the judge synthesizes only from round 2. Anything that doesn't hold up in the cross-examination doesn't get to drive the verdict. It turned the output from a clean yes/no into a much deeper, debated call. Tweak 2 — bringing in other LLMs. Nate's version runs on Claude alone — one model playing all six personas. I wanted more than one point of view at the table, so I added other LLMs to the panel: Codex (GPT) and Gemini, alongside Claude. Now Codex and Gemini run the adversarial panel and cross-examine each other in round 2, while Claude handles the live web research and acts as the judge. Three different brains genuinely disagreeing gives me sharper feedback than one model talking to itself.

Well, this 49 year old single mum of 3, who also cares for her elderly father and has days that are so insanely full, and brain fog that is absolutely debilitating most days is LOVING this journey. I've wanted to build another business since becoming a single mother but it's just been too hard... and Claude Code has literally given me my life back! And now I'm deep in setting up Hermes ... had some hiccups with making it talk to my Claude Code assistant but I'm slowly getting there. I've used AI daily since November 2022 but I have never learnt as much as I have from Nate over the last few months! Thanks to this amazing mentor and community, I'm about to launch my business! And I am SO passionate about AI because without it, this would have been IMPOSSIBLE for me! Thank you so much Nate and to ALL of you! So grateful for places like this where we can connect.

I signed a contract with my first client. This is a huge joy for me. I have been a real estate broker for the last 11 years, so I focused on creating an AI agent for such agencies. Is there anyone else who is doing something similar. I would be happy to help each other. 🙃

👋 Quick intro, and a real ask for the builders in here. I'm not here to sell AI agents or my time — honestly the opposite. I'm an operator. I run a publishing business (mostly children's books on Amazon, multiple pen names, three LLCs, high six figures($600k+ per year and climbing toward seven). I'm here to ask — because the people in this group know AI things I need, and I'd rather partner with someone good than figure it all out alone. Here's the goal: turn the whole operation into a machine I mostly just monitor. I look at the niche research the Ai agent has done then hand another agent the brief, and the system produces a genuinely good book, creates all visual assets+audiobook, runs the marketing etc. Here's where I'm at. ⬇️ 🛠️ WHAT I'VE ALREADY BUILT (and want to refine) I'm not starting from zero. These already run as skills in Claude Code: ▪️ Amazon niche research — I feed a raw keyword export into an agent and get back the market gaps, the complaints mined from competitor reviews, and a book concept. ▪️ PPC + ad automation — my bid rules, negation logic, and weekly cadence are written into skills the agent runs against fresh ad data. (This is the heart of the business — ads are ~80% of my costs.) ▪️ Listing SEO — title, subtitle, description, and backend keywords, built as a writer/editor agent loop. ▪️ Weekly review — pulls from my tools and tells me what actually moved. So I know how to build skills. I want to go much bigger. 👇 🚀 WHERE I WANT TO GO NEXT (this is where I need you) 1. Books that are actually GOOD — not AI slop. 📚 Produced at scale, across different niches. This is the hard part and the one I care about most. I want manuscripts readers genuinely rate, not the obvious AI junk flooding Amazon.(I'm thinking something like a agent loop/goal that has a writer and editor looped agent and feed it other best selling books so that it gets the style and format down, but irons out all the shitty AI language and quirks.) 2. Pro-level covers with AI. 🎨