I built a system. It teaches AI how to build visual identities. It doesn't drift. Here's the story: I used to hand-build every visual identity myself. Client work. My own channel. Same routine every time. I explained the colors again. I explained the mood again. Nothing carried forward. Then I tried AI. Same brief, ten times. Ten different looks. One shot came out "noir". The next looked like a postcard. Same words in. Different result out. The model forgets. So I changed the approach. I stopped writing better prompts. I started building in stages. 3 stages. Each one builds on the last. Stage one locks the idenity. Color. Material. Type. The rules for how they combine. Stage two runs that identity through real scenes. A person. An object. A place. An idea. Same rules. New subjects. Stage three puts it in motion. It reveals. It connects. It transforms. Same materials. Same colors. Now it moves. Nothing gets re-explained. Each stage hands its work straight to the next. Drop them in Higgsfield. Prompt each scene. Full animation - no style drift. I tested it on a style I'd never planned to use. "Archival Investigative Montage." Ran it cold. It came out the same quality as everything else. That's the test that mattered. Not the polished demo. The one I didn't prepare for. Are you building multi-step AI systems yet? Or still prompting one shot at a time?

Hey there, does anyone know where Jake posted his system regarding how he set up and does his video content folder set up etc.

A founder asked me a question this week that I couldn't answer on the spot: do other businesses have a system like this? So I went and looked. Short version: outside this room, I can't find them. Everyone here runs some version of it already, a folder of markdown that Claude reads and maintains, and I'd stopped noticing how unusual that is. I'd like the room to tell me where the others are hiding, or whether we're further ahead than we think. The system in question is the one I've been installing at a three-person shop since August. The part that's now real: a knowledge base in a git repo that their own Claude reads before it does any work, a file register that watches their Drive and logs every arrival and every move, and a pitch engine that runs a brief through four human approval gates with the gaps written on the slide. Every filing carries who approved it or which rule filed it. Every page carries where it came from. When something ends up in the wrong place, the record says whether a person put it there or our rule did. None of the pieces are exotic. Markdown, git, a spreadsheet, an Apps Script, skills. What's different is that the knowledge is compiled and maintained, not retrieved. The agent doesn't search a pile of PDFs every time. It reads pages it helped write, with the provenance on them, and the rules for what it may and may not do live in the same repo. Here's what I found when I went looking for who else does this. The big holding companies in that industry have "operating systems" now. Real ones, sold to clients as the reason to hire the group. That's a data platform with agents on it, top down, owned by the group. Not a thing three people could own. Everyone in the middle has AI on top of files. The numbers from this year's surveys: about two thirds of agencies run brief generation in production, a third draft client reports with it, and the single biggest problem the independents report is getting AI into their actual workflows. Every "AI knowledge base" guide I read describes the same thing. Search over the shared drive. A memory server. Chat with your documents. Useful. Also not a record of anything.

I'm curious: who here is using Obsidian for their knowledge management and integrating it with an ICM setup? I'm looking to combine my local markdown vault with AI agents to build a permanent context layer, and I'd love to get your thoughts: 1. How do you integrate them? (e.g., using the MCP filesystem server, specific Obsidian plugins, or custom local scripts?) 2. What is your honest opinion on this? Is it seamless, or does the AI get bogged down once your vault grows and files get messy? Any tips on folder structures (like separating an /Inbox from a /Core folder) or system prompts that keep the agent from messing up your notes would be highly appreciated. Thanks!

Hi everyone, For those who have used both Claude Code and Codex through their subscription plans, is Codex actually better and faster for vibe coding? I have been using Claude Code on a subscription for a while. It is often very capable, but I have found it extremely slow. I switched from the Mac desktop app to VS Code, hoping it would improve the experience, but many tasks still take a very long time. Lately, I have also noticed more mistakes and patches that frequently break things. I am now spending more time debugging and repairing its changes than making progress on my projects. I have tried several Claude models, including Fable 5, Opus 5, Opus 4.8, and now Fable 5.1. I have heard that Codex is faster and more efficient, but I would appreciate clarification from people who have used both: 1. Can Codex be used through a subscription, such as the $200 ChatGPT plan, with coding limits comparable to Claude Code? Or does extensive use require separate API billing? 2. Is Codex genuinely faster and more reliable than Claude Code for vibe coding? 3. Can Codex take over projects that were started in Claude Code by reading the existing codebase, `CLAUDE.md`, and other Claude project files? I would especially appreciate feedback from anyone who has used both platforms extensively on real projects. Thank you so much for your help.🙏