User
Write something
30 Min Q&A - Bring Your Mess is happening in 8 hours
One folder, one plain note
The tempting first move is to ask the AI to deal with everything at once. The whole Desktop, every download, three years of chats. That's a lot to hold, and it's the wrong place to begin. Begin with one folder and one note. That's the whole first step. 𝗧𝗵𝗲 𝗺𝗲𝘀𝘀 𝗜'𝗺 𝘂𝘀𝗶𝗻𝗴 𝗮𝘀 𝘁𝗵𝗲 𝗲𝘅𝗮𝗺𝗽𝗹𝗲 This is a demo folder I built for filming. None of it is real. All of it is familiar: a fake Desktop, Documents and Downloads with 141 files between them. On the Desktop there are four versions of the same idea: ideas.docx, ideas_final.docx, ideas_final_v2.docx and ideas_FINAL_actually.docx. There is a "New Folder", a "New Folder 2" and two folders called "untitled folder". Documents has Backup and Backup (1), Projects and Projects NEW. Downloads has resume.pdf, resume_FINAL.pdf and resume_v3.pdf. Open any of them and nothing says which one is the real one. A person would have to ask you. So would an AI. 𝗧𝗵𝗲 𝗶𝗱𝗲𝗮, 𝗶𝗻 𝗼𝗻𝗲 𝗹𝗶𝗻𝗲 It comes from Jake Van Clief's ICM, the Interpretable Context Methodology: a folder tells the AI what to read, so the AI is not carrying everything in its head. What you'll find in SKOOL is how I use it in my own work, and it starts with the step below. 𝗦𝘁𝗲𝗽 𝟭: 𝗺𝗮𝗸𝗲 𝗼𝗻𝗲 𝗳𝗼𝗹𝗱𝗲𝗿 Pick one thing you are working on. Not your whole computer. One thing. In my demo it is the workshop outline, because two files for it are sitting on the Desktop: workshop outline.pages and workshop outline OLD.pages. Make a new folder and give it a plain name. I call mine "Workshop". Copy those two files into it. Copy them, don't move them. Your originals stay where they are, so nothing can go missing. 𝗦𝘁𝗲𝗽 𝟮: 𝘄𝗿𝗶𝘁𝗲 𝗼𝗻𝗲 𝗽𝗹𝗮𝗶𝗻 𝗻𝗼𝘁𝗲 Open a plain text editor and save a file in that folder called "start here.txt". Write it the way you would explain things to a friend who is about to help you. Mine says: > This folder is for the workshop I'm planning. > "workshop outline.pages" is the current one. > "workshop outline OLD.pages" is the earlier version. Keep it, but don't use it.
0
0
One folder, one plain note
A one-page sheet: session notes into a follow-up message
I paid $9 for a course on AI & Video. The handouts were good. One of them had twenty prompts to paste in your offers, your scripts, your landing pages. None of its eleven files said what to leave out. If you teach or coach, what to leave out is the part that matters. Your session notes are about a person. So here is one page for one job. Session notes in, a short follow-up message out, nobody's details in the chat. 𝗧𝗵𝗲 𝗳𝗶𝗹𝗲 Notes-into-a-follow-up.pdf. One page: three lines on what never goes into a chat, one template with a made-up example, five fixes for when the reply comes back wrong. It works in any AI chat. You do not need a particular tool. 𝗛𝗼𝘄 𝘁𝗼 𝘂𝘀𝗲 𝗶𝘁 1. Read the three privacy lines first. 2. Copy the template below and fill the brackets from your own notes. Use initials, or "a client". 3. Read the reply aloud. Anything you would not say to them in person, cut. 𝗥𝘂𝗻 𝘁𝗵𝗶𝘀 𝗼𝗻 𝘆𝗼𝘂𝗿 𝗼𝘄𝗻 I -------- to --------- Here are my rough notes from today's session with [initials, or "a client"]: [paste your notes, with no health details]. Write a short follow-up message from me. Say what we worked on, give them one thing to try this week, and invite a reply. Keep it to [4 or 5] sentences in a [warm, plain] voice. Do not promise results, and do not give advice that is not in my notes. Avoid [words you never say]. Give me one version only. If anything in my notes is unclear, write "unknown" instead of guessing. Try it on one real session this week. Then tell us the first thing the reply got wrong. Your answer decides what the next sheet fixes.
1
0
A one-page sheet: session notes into a follow-up message
Every new chat, you introduce yourself again.
Who you are. What you sell. Who it's for. How you like it worded. You type it into a new chat. The answer's fine. Tomorrow you type it again. The fix is a file. One page about you, written once. It holds what you do and who it's for, what you never want said, and a few sentences in your own voice. Don't know what to write? Answer questions out loud and let the answers become the file. That's how the Quiet Scribe Suite begins. Your file is plain text, and it's yours to edit. Write your first three lines today and put them in the comments.
0
0
Every new chat, you introduce yourself again.
A citation that exists isn't the same as a citation that's right
I built a small auditor that checks a marketing email against the CAN-SPAM rules and quotes the regulation for every finding. Every quote was verified, so I thought it was safe. The judges' feedback found the hole in one line: "a citation that resolves but points at the wrong thing is the exact failure this competition is hunting." My checker confirmed each quote existed somewhere in the reference files. It never checked that the quote sat under the section the finding cited. Cite the wrong section, keep the right words, and it still printed "quote verified". The rebuild checks each quote only inside the provision its citation names. Before writing any code, I committed eight questions taken from the feedback, so the test couldn't drift toward the answer. The original passes 2 of 8 and the rebuild passes 8 of 8. Those are questions I wrote myself, so the score isn't independent, and the repo says so. The results file also lists what's still weak. One check is a word list, and it gets "your account number is not needed" wrong because it can't read negation. I'd rather publish that than have someone find it. If you're running any AI step that cites a source (a policy, a contract, a style guide), the same hole is probably there. Checking that the words exist is the easy test. The useful one checks that they're where the citation says. Try it yourself: take one cited output, change only the section number, and run your check again. If it still passes, you're checking existence, not location. Question for the comments: what are you citing in your builds, and how do you check it? Free, MIT, nothing to sign up for: https://github.com/NFTYoginis/can-spam-auditor-rebuild
0
0
A citation that exists isn't the same as a citation that's right
Do you need another bot, or a clearer folder?
Two layers keep showing up in the setups I've seen. Folders underneath (each one a job, a file for what comes in and out, a log of decisions). Named bots on top, one per job or login, quiet unless something needs a yes. I run both, the second lighter: my workers get dispatched, not kept running. A brief goes in, a report comes back as a file. Here is what I'd copy from the bot side, and it needs no product at all: One owner per login. Nothing goes out as you without your yes. Every decision gets written down. If nothing changed, say nothing. And here is when I think a bot earns its place: a screen with no other way in, a watcher that has to run for hours, something that must happen while you're away. Everything else, in my experience, a clear folder handles. Which are you running right now, folders, bots, or both? And what was the job that made you add your first bot? The full piece: https://thequietai.com/writing/agents-or-architecture
Do you need another bot, or a clearer folder?
1-22 of 22
powered by
Coach More. Work Less.
skool.com/wellness-ai-6404
For coaches tired of doing it all
Create content, organize client work, and reclaim your time with your own AI team
Black Friday giveaway
Build your own community
Bring people together around your passion and get paid.
Powered by