My sister Hannah and I just finished something we’d never done before: the AI visuals for a live concert, Hello America, on the giant LED wall at the Colosseum at Caesars Palace in Las Vegas. Thirty songs in ten days. A big part of how two beginners pulled that off came from right here. ICM is how I ran it: one folder, one set of notes and one chat per song, more than thirty chats running at once, each one picking up where the last one left off. Thank you, Jake, Matthew and the whole Eduba team for building this and sharing it so openly. And @Matthew Creamer , a special thank you for coming out to the show in person. Showing up at the gala and the show to support us meant more than I can say. Having someone from this community in the room made it real. We captured the whole journey, the good and the messy parts: the tools I built, what broke, about 55,000 credits, and how ICM held it all together. ▶ Watch it here: https://www.youtube.com/watch?v=-HiJLMo3HfQ If it’s useful to you, a like and a subscribe would mean a lot. It helps me keep making these breakdowns for you.

I compared @Jake Van Clief ’s animation workflow with a Short I made called “The Box Nobody Wanted to Open.” Jake’s saved system uses Canvas/JavaScript, Python, Playwright and FFmpeg. My Box was built with Python/Pillow, NumPy and FFmpeg. Both use a timed plan and export checks, but I haven’t found evidence that the Box ran through Jake’s engine. The useful discovery: my “preflight” checked a short clip only after the entire video had rendered. Next time I want to render and inspect a short section first, then commit to the full render. Simple change, potentially less wasted time. I’m learning that the point isn’t necessarily to replace one workflow with another. Sometimes it’s to understand what each does and borrow the part that makes the work better. For those making videos with code, what do you check before committing to a full render? @Danney Tee

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.

Hi Guys id be really interested to see if anyone is using GROK as the orchestrator and how theyre directing it using the ICM method that Jakes teaching us about, im a novice user and just started my journey, Im trying to direct it to use my claude code subscription for the lessor or other agents, and reduce token usage, but Kelly (my chief of staff) which uses grokbot harness is my orchestrator, , any videos would be greatly appreciated or help. thanks in advance.

🙋 A little about me: I am the owner of Easton Film Co, a wedding videography studio based in Birmingham, Alabama. We work mostly across the Southeast, with a contractor team of shooters and editors. 🎯 My current goal: By April 2027, I want to run the whole business from an AI-first HQ, including video editing. Then, with enough approvals, I want the entire business to be automated with humans in the loop only at critical points. 💪 What I'm currently building/working on: I'm building the HQ with a set of custom Claude skills for my studio. They cover lead intake and appointment setting, proposals, call follow-ups, wedding project setup, and multi-party call scheduling. 🤔 My biggest struggle or question right now: Everything still feels fragile. Something might work at first, but given a few weeks things break down and I find myself maintaining more than building. How are you all handling rule governance, testing, and monitoring so your systems stay reliable as they grow? Let's get it! 🚀