Three days into Implementation Playbooks. I want to know what came out of it. Not what you watched. Not what you understood. What did you actually MAKE? - An animation you finally got working? - A folder structure that finally makes sense for your AI setup? - A browser workflow that's saving time? - Or something else entirely? Drop it below. Doesn't matter how small. Some of the most useful things in here started as the smallest outputs. And if you got stuck on a step... Don't sit there spinning. - Bring it to the Clief Notes AI - Bring it to the next call - Go back to the lesson and figure out WHERE you got stuck. That's part of the build. The roadmaps aren't here to make you feel like you completed something. They're here to make sure you walk out the other side with something you can actually use. Drop what you built below. 👇

We officially launched the new Clief Notes Agent, and I wanted to check in with you. Have you had a chance to talk to it yet? If you have, I’d love to hear how it went. And if you’ve run into any questions, confusion, or issues getting started, drop them in the comments below. The goal is to make it easier to find what you need, know what to focus on next, and get more out of everything already inside Clief Notes. So, How’s your experience been so far?

A model reviewing its own work is not a review. It is the same judgement run twice, and it agrees with itself both times. - Maker and checker are separate passes - whatever produced the work does not get to grade it. - Fresh context, not just a fresh prompt - a different chat, ideally a different model, carrying none of the reasoning that built the thing. - A number it cannot argue with - a test, a diff, a count. Prose review on its own will find reasons to approve. The failure mode is not that a model lies to you. It is that it is still holding every assumption that produced the work, so asking whether the work is good just reasons forward from those assumptions and lands where it landed the first time. I have had this go wrong with real stakes on it. Folder bloat that survived an adversarial review and two further passes on the strongest model I had. A multi-repo restructure proposed off one of three files the model had actually read. A Git migration recommended on the grounds that we had a backup, which we had made ourselves an hour earlier. Every one of those cleared a self-check first. What changed it was making the check structural rather than something I remember to do. In my YouTube workspace no finding enters the register until it has been surfaced to me at the close of the query that produced it, so the system proposes a belief and a human commits it. In phronesis the distillation pass runs behind an eval gate allowed to reject the commit outright, so the pass that writes the profile is never the pass that decides the profile is good. Metrics carry the other half. A verdict written in prose can always be argued into place, a count or a failing test cannot - if the only evidence something worked is a paragraph the model wrote about its own output, there is no evidence. Where has a self-review waved something through that it should have caught, and what do you actually use as the outside check - a second model, a fresh chat, a test, someone else in here? More interested in the practical setups than the principle.

It’s live. Starting today, everyone in Clief Notes has access to the new Clief Notes AI. The easiest way to use it? Don’t overthink it. Ask it the question you would normally ask me. “Where should I start?” “What should I focus on next?” “Where did you talk about [topic]?” It’ll use what’s already inside Clief Notes to help answer you and point you toward the right lesson or resource when there’s something worth going deeper on. The goal isn’t to give you another AI tool to play with. It’s to make everything already inside this community easier to actually use. If you want Access to it Comment "READY" and we'll send you access to it!

I Kept stopping. I’ve been going back and forth trying to learn Jake's ICM. I would start. Feel overwhelmed. Stop. Then come back and repeat the same cycle. I would hear words like harnesses and MCP servers, API, automations etc. It wasn't that I couldn't learn it — it was that the list kept growing faster than I could get through it, and everyone seemed further ahead every week. Honestly, it became too much So I stopped. Then I came back to the community one day and started looking through Jake's Weekly comps. briefs, repos, winners etc. He said something along the lines of: "Pick a real workflow that belongs to you. Don’t build for a fake client this time" That made everything click. 💡 I already had a real workflow. I’m a solo architectural visualisation artist. Every new job requires quotes, invoices, project folders and client emails. So I built Workstation around that. THE OLD WAY ❌ A client email would arrive. I would: 1. Open Canva on another screen. 2. Manually enter every detail into a quote. 3. Triple-check everything then Export the PDF. 4. Write the response email. Repeat the process for two separate invoices. It took hours for the entire set. Sometimes I would find a mistake and check everything again. When a client asked for an imagery proposal, I felt a bit anxious if I'm being honest, because I knew this mess was waiting for me. Yes, I was creating invoices manually in Canva. I know. Insane. But that was my system. THE NEW WAY ✅ Now I paste in the client’s email. Workstation handles the rest: Client email Extract the job details ↓ Calculate the price ↓ Create the project folder ↓ Build the quote ↓ Build both invoices ↓ Render the PDFs ↓ Prepare the client email ↓ I check and send What previously took hours now takes minutes. HOW IT WORKS The system uses simple folders and Markdown files: 📁 00_intake: Reads and organises the brief 📁 01_quote: Builds the quote 📁 02_invoices: Builds the invoices and PDFs 📁 03_email: Prepares the emails on my dashboard