Activity
Mon
Wed
Fri
Sun
Dec
Jan
Feb
Mar
Apr
May
Jun
Jul
Aug
Sep
Oct
Nov
What is this?
Less
More

Owned by Gabriel

For coaches tired of doing it all. Create content, organize client work, and reclaim your time with your own AI team. Powered by The Quiet Scribe.

Synthesizer
47.4k
Free
Skoolers
148.9k
Free
Clief Notes
55.6k
5.0
Free
94 contributions to Coach More. Work Less.
What's the one thing you'd hand off first?
I'm working out what to lead with for coaches. If you could hand one job to an AI assistant tomorrow, which would it be? Email triage. Replying to emails. Follow-up after a call. Notes from discovery calls. Posting content. Something else. Tell me the one that would give you back the most time, and what it costs you now.
0
0
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
The one page I keep beside me on calls
When someone tells me how their week "usually" goes, I get a story. When I ask about the last time it happened, which day and what they opened first, I get what actually happened. Those are rarely the same thing, and the gap between them is where the real problem sits. So I made one page to keep beside me on discovery calls, with coaches, teachers, anyone who wants help with their week. It's attached: a square preview, then the full sheet (it prints on US Letter). The moves are adapted from Jake Van Clief's discovery drill, and the layout is ours. 𝗧𝗵𝗲 𝘁𝘄𝗼 𝘁𝗵𝗮𝘁 𝗰𝗮𝗿𝗿𝘆 𝘁𝗵𝗲 𝗰𝗮𝗹𝗹 Step 2: "When was the last time it happened? Walk me through that one." Step 3: "Any other time it didn't work?" Ask it twice. Then say nothing. I've told yoga students for years that silence draws attention to your voice. On a call it does the same for theirs. It gives them room for the one they nearly kept back. 𝗛𝗼𝘄 𝘁𝗼 𝘂𝘀𝗲 𝗶𝘁 Go in order, one to six. Write their cost in their exact words. Don't bring up AI or any tool; let them get there. Step 6 is only for someone who asked for help or showed you a real problem, and it has a blank where your own price goes. After the call, take two minutes: write "not asked" beside anything you skipped, because a blank reads as "no" next week. 𝗪𝗵𝗲𝗿𝗲 𝗜 𝘀𝘁𝗶𝗹𝗹 𝘀𝗹𝗶𝗽 Without the page in front of me, I drift back into "so how does it usually go?" That's the whole reason it's one page. 𝗧𝗿𝘆 𝗶𝘁 𝘁𝗵𝗶𝘀 𝘄𝗲𝗲𝗸 On your next conversation with a client or student, swap one "usually" for "when was the last time?" and notice what changes in the answer. Which step would be hardest for you to say out loud?
The one page I keep beside me on calls
0 likes • 8d
@Arne-Per Heurberg I find use with such questions every day actually. I favor asking my team odd questions and see what comes out. In real life conversations, there are usual questions like "where are you from?" that after living in so many places all my life, I find that question is just rhetoric. My answer usually is "from my mother's belly." Making for the topic that the answer is half of the question.
Game Time: Finish this line: "I know what I want to say, I just never ___"
𝗧𝗵𝗲 𝗴𝗮𝗺𝗲 Finish the sentence in the comments: "I know what I want to say, I just never ___." Some answers will be about time. Some will be about where to start. A few will be something I hadn't thought of. 𝗧𝘄𝗼 𝗿𝘂𝗹𝗲𝘀 One line only. No fixing it afterwards. What's yours? One line is plenty. Made with The Quiet Scribe team.
1 like • 10d
@Arne-Per Heurberg do you find that AI makes that part easier?
0 likes • 9d
@Arne-Per Heurberg that is a good observation.
1-10 of 94
Gabriel Azoulay
3
10 points to level up
@gabriel-azoulay-3254
Wellness Professional, Yoga and Thai Massage Master Educator who loves building with ICM and solving your problems, physical or digital.

Active 31m ago
Joined Oct 2, 2026
Khao Lak, Thailand