Have you ever seen a creator and want to know more about the creator, But instead of doomscrolling, what if you could search through their content ? That is what I have built. It's essentially a RAG that I have fine-tuned after scraping my one of my favourite creators content on Instagram. So in case you want to understand, What did this particular creator opinion on MCP servers or anything else, all that information you will be able to get in 10 seconds along with the reel where they mentioned that exact information. I'm trying to establish if what I built has a product market fit. So let me know your thoughts in the comments.

I run tech for Cafe Takeover, a weekly events series in Delhi. For our last event I wanted to ship something that is never done in my city before — instead of a DJ or a trivia night, the entire room playing a live multiplayer game on their phones. A live Among Us / Mafia mashup with hidden imposters, sabotages, and players hunting each other in real time. 4 days. React + Firebase/Firestore. Solo. ~80 concurrent players the night of the event. No crashes, no lag spikes. Firestore bill didn't go beyond 3₹. A few things I'm proud of: → The matchmaking. Pairing two players inside a room of 80 all hunting at once. A queue holds requests for milliseconds, pairs the first two compatible players atomically, and writes the match to both docs in a single transaction. No double-pairs, no stale opponents. →The imposter loop. Imposters trigger sabotages that hit every phone in the room within a second. Players can guess imposters back — wrong guess and you're locked out for 2 minutes with a full-screen countdown. The whole cat-and-mouse runs entirely off Firestore state, no server, no socket layer. →The admin panel. Real-time control surface giving me live visibility into the running game from my phone — who's alive, who's blocked, who's winning, manual override hooks for when something weird happens in the room. Saved the night twice. →The atmosphere. 16 personalities, 5 sabotages, atomic leaderboard scoring. Enough variation that no two rounds played the same. The end result: 80 strangers, an hour of nonstop hunting, every phone in the room locked into its own private duel. People who weren't there are still asking when the next one is. Massive thanks to @Jake Van Clief . Genuinely couldn't have shipped this in 4 days without the methodology. The CONTEXT discipline is the thing — when something broke at 2am I traced it to one file in seconds instead of digging through a tangle. That's what bought me the time to actually polish the game feel instead of fighting my own codebase. First project where I actually saw the impact

There have been some good questions in my previous posts about my agents, so I want to clear up a few things. I call them agents because it helps me think and stay organized. But strip the jargon and here's what's actually happening: a folder with the right files in it tells an AI who it is, what it does, and what good looks like. Unix figured this out a long time ago. I remember working on mainframes in my early 20s. Files in folders. It wasn't powerful because it was complex. It was powerful because it wasn't. Unix came out in 1969; I was using it from 1998 to 2002. The "writing room" is a folder. Cash lives in it. His instructions, his guardrails, his examples, his voice reference — all files. The AI reads the folder and knows how to behave. The room gives it context. The files give it structure. I have 15 of these rooms. Duke orchestrates between them. The naming isn't the point. The structure is. Here's the part most people miss: almost every agent in my system has a human counterpart. A real expert whose domain knowledge shaped the instructions — and who can tell me when the agent gets it wrong. Cash's counterpart knows copywriting. Trace's counterpart knows data. That feedback loop is how the system actually improves. You're not building AI. You're building infrastructure. Build the foundation. Build the structure. The agents are just what you call it when the rooms start working together. My lesson: don't copy me, don't copy Jake, we all learn from each other, and then you make it your own. Stick to the fundamentals. Watch Jake's videos; it will rewire your brain and change how you think about AI. There are no shortcuts. You have to build a foundation first. Links to referenced posts: https://www.skool.com/quantum-quill-lyceum-1116/visualized-my-agent-team https://www.skool.com/quantum-quill-lyceum-1116/the-folder-system-became-my-agency

This is a new style as well that I'm testing and I'm talking about systems thinking a little bit more in it and how I think that you can do more as a company now, especially if you're a consultancy. If you're thinking of starting your own or already have one, this video might be huge value for you! It's on my YouTube so if you can go like it there and leave a comment that would be amazing I'll probably create a text companion and make a few more videos and add this to a new series called systems thinking In the classroom! We shall see.

Bottom line: Two hours. Jake's frameworks went from a folder to live tools running in my workspace. Most community content has a 48-hour half-life. You read it, save it, and it ends up somewhere it influences nothing. The content is fine. The structure is the problem. Here's what I did: --Organized the vault: Cleaned up 30+ scattered files, classified by type, split into five sections. A file you can't find in 15 seconds doesn't exist. --Built an auto-ingestion pipeline: Scheduled task runs nightly. Drop anything new into _Inbox, it classifies and routes itself. New content stays in its lane. --Converted three frameworks into live skills: - Council of 5 — runs on command. Five advisor perspectives on any decision, simultaneously. - 60/30/10 Triage Rule — installed into workspace operating rules. Applies to every task without prompting. - Discovery Call SOP — no longer a document you read mid-call. Phases through pre-call, live support, and debrief automatically. --Audited workspace documentation: Cut 30-40% from routing and context files. Tighter files, faster responses. Before: Jake's frameworks lived in a folder. After: three of them are running. The best part is that it compared it against what my current business needs are and filtered out resources that weren't relevant to me (yet). For example @Curtis Hays full agency or @Roc Lee and his awesome conference talk engine. If you want to replicate it, I've attached a step-by-step guide with the exact prompts I used across all five sessions. Thank you ALL for your inspiration and to @Jake Van Clief for building this incredible community.