Tell us three things: 1. What you do (job, industry, student, career-changer, whatever) 2. What brought you to Clief Notes 3. One thing you're trying to figure out right now related to computing or AI I'll respond to every single one. And read each other's intros too because the person who's stuck on the same problem as you might already be in this thread. I'll go first I am Jake, I have been working in tech for 15 Years, building with Generative AI for 3 Years straight now! Excited to teach and learn! That's it. Simple, scannable, gives you data on who's joining and what they need, and keeps the feed clear for content that retains people past week one.

Does anyone know when the live sessions are for VIP or where they are advertised?

Hey Everyone! Hope you're enjoying you're time at Clief Notes! Recently we've had our first Afternoon Tea with Joe Firamonte, founder of Dark Square and Constellation. Joe has spent 2 decades helping billion-dollar companies think through AI strategy before it was a buzzword. His tool Constellation turns mood boards into scalable behavioral data, letting thousands of people respond to imagery in a way that was never measurable before. This will be a 5 part series of multiple pieces of notes you can take as reference. As usual, Day 5 will have the biggest drop of value from the webinar! HOW CONSTELLATION SCALES VISUAL DATA From our webinar with Joe Fioramonti, here's how they solve the visual preference problem: THE STACK: INPUT LAYER - Curated mood boards (6-20 images per board) - Drag-and-drop interface (green = like, red = dislike) - URL-based segmentation for demographics - 2-minute timer tracking decision flow PROCESSING LAYER - Heat map generation (preference clustering) - Time-series analysis (first vs. last choices) - Correlation filtering ("show me what people who liked X also liked") - Comparison arrays (liked vs. disliked vs. contested) ANALYSIS LAYER - Semiotic discipline frameworks - AI pattern recognition models - Threshold-based filtering (risk tolerance) - Demographic cross-segmentation OUTPUT LAYER - Interactive heat map visualizations - Downloadable data exports - AI-generated interpretation reports - Stakeholder-ready presentations KEY INNOVATION: Captures preference at the VISUAL level—before language, before rationalization. Why It Matters: People recognize meaning before they can articulate it. Traditional surveys miss this. APPLICATIONS: ✅ Brand identity testing ✅ Retail product preferences ✅ Legal jury selection (!!) ✅ Entertainment creative direction ✅ B2B employee insights The platform turns subjective design into objective data. What do you think, does this feel more smooth then most 2 line claude prompts?

Hi everyone, i’ve just joined the community after seeing how qualified and intelligent the owner is and i’d like advice. quick backround, ive been AI consulting for 2 years now. hasn’t been great because of where i am, hard to get people to pay for something they don’t even know they need, then when working internationally the CPAC is just too high for me and the outreach softwares cost me too much so im at a standstill. but anyways from there im using my skills now for the last 3-4 months on building and app. My current setup is building the app on bolt.new (which i realised now was a terrible idea), and using claude as well to help me make changes and fixes once my credits run out on bolt. ive got my database connected through bolt, and my domains connected as well. I actually want to move off of bolt but dont really know how to, and i want to optimise my work in general because right now its really sloppy and claude makes so many mistakes before it fixes the issue but im only on the $20 plan so my limits get hit so quick. then on the other side of issues, its difficult to make a native app from a bolt creation from my knowledge, so i wrapped it in capacitor so that i cant just also straight up direct it to the web app but thats got its own issues and i dont think apple will allow that on the app store. so my questions are: 1- any advice for the consulting business? 2- i really need advice for optimizing my work process, how do i do it? (claude.md? ,skills? , how??) 3- how can i move off of bolt.new and self host it all without breaking things? 4- what would be the best and fastest way to make my web app a native app store/play store ready app? (its react native) thanks in advance. looking forward to hearing responses. @Jake Van Clief

No App, No typing, No training needed... Just speak --> get a professional PDF Invoice in second. Here the workflow : 1. Contractor sends a voice message on Telegram 2. Whisper AI transcribes it 3. GPT-4 extracts items, quantities, prices 4. A professional PDF invoice or Angebot is generated automatically 5. Bot sends the PDF back instantly on Telegram Full stack running in production: → n8n on Hetzner VPS 🇩🇪 → HTTPS via domain kinvoice → Telegram Bot as the UI → html2pdf for document generation → Multi-document support (Rechnung + Angebot) The contractor doesn't need to learn any software. They just talk. The bot does the rest. This is what I'm building for German SMEs — simple AI automation that saves hours every week. Onboarding first customers now.