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

Memberships

AI Automation Society

407.5k members • Free

Clief Notes

38.8k members • Free

Agentic Academy

1.5k members • $37/month

Story Hacker AI

1.6k members • $67/month

ChatGPT Users

12.7k members • Free

GC
Growthworks Community

24k members • Free

Ghostwriters Anonymous

16.9k members • Free

9 contributions to Clief Notes
How do I get access to discord group after upgrading to premium?
I know this is probably a dumb question, sorry in advance for having to ask. How do I get access to discord group after upgrading to premium? Thanks!!
🏁 Foundations 4.5 Check-In
You just saw how context changes per task. Vote below, then tell us in the comments: what two areas of your work did you set up, and did Claude behave differently in each one?
Poll
236 members have voted
0 likes • 19d
My problem before this course (which I could not identify or appreciate until now) was that I had a giant Claude.md file that covered the entire project. It provided much useless information each time I attempted a task and the outputs drifted. I forgot that the best way to eat an elephant is one bite at a time. I am in process of breaking apart my MOA ( Mother of All) MD files into smaller context specific Claude.md files that reside in their appropriate folder in the workflow. Orchestration of necessary information for completion of a task via the routing table streamlines workflows, improves token efficiency, and improves outputs. I am getting it clearly now!
🏁 Foundations 3.3 Check-In
Everyone gets something wrong the first time. Vote below, then drop your mistake in the comments so others can learn from it.
Poll
450 members have voted
1 like • 19d
My issue was converting an existing free form project that had some structure but not a structure that utilized the folders as the workflow cleanly. I have had to go back and evaluate the folders and flow through the lens of this course and revise accordingly
🏁 Foundations 3.1 Check-In
You just watched the full 23-minute folder architecture walkthrough. Vote below, then drop your use case in the comments. What are you building this system around?
Poll
857 members have voted
0 likes • 20d
This video was extremely helpful. I am currently trying to leverage the folder approach on a project to analyze an opposing party’s attorney fees and costs in an arbitration I unfortunately lost. I have to perform the analysis under eleven or so cases that control how a prevailing party can claim attorney fees and costs. The old way was reviewing line by line and creating spreadsheets based upon the analysis from each case applied to the fees and costs sought and then combining all the analysis tracks into a complete analysis with justification for allowing, disallowing or reducing proposed fees and costs and preparing a memorandum on same. My first run (before finding this group) was in Claude, bit the limitations of chat were too great to get a reliable outcome. So I found the option of ClaudeCode. My first attempt with Claude Code blew through tokens and the project would degrade as I went through each phase of analysis ( tried doing it in one continuous session) the end result was the billing analysis was full of inaccurate results. I then took a second shot at it and tried to break it down into smaller chunks ( again before the group). I also started to have Claude after each conversation phase create a resume.md so that it would create a jump off point for our next conversation and continue from where we left off with the knowledge necessary to execute without having to burn tokens to get up to speed. I also at this point created a process where it would evaluate how it performed the round and make recommendations on how it can improve its efficiency and quality of outputs ( After Action Report). I would then take this after action report and have it update the MD files used to incorporate the suggested improvements. At that point, I would start the next phase. The outputs become more consistent and defensible, which is what I wanted, but there were issues where small nuances were being missed in the analysis. I would have to go back and try to iterate from the point of failure and redo several phases to get to an improved end result. Better than the old way of doing this analysis by hand with spreadsheets ( in this use case I am dealing with six years of billing records and cost records which is voluminous). Here I am now, creating folders with opposing party billing and cost resources, our billing and cost resources, controlling case law ( each case is now distilled into an MD file that outlines how fees and costs are determined under that specific controlling case), draft outputs, final outputs and briefing on outputs (actual initial drafts of memorandums and spreadsheets that have case cites, categories of fees and costs and spreadsheets backing up analysis for final editing) I am still having it go through a After Action Report stage and self improve efficiency and outputs. I am still plugging away at it, doing the course. here and then revising and improving this project based upon what I am learning. It is slow but I see improvements. I also see a potential commercial application for this project when I have it complete and battle tested. This is definitely a different way of thinking for me from my day job, but I am seeing ways that this thinking can improve my day job. I am an old dog learning new tricks!
🏆 WEEKLY COMP #6: THE RESEARCHER 🏆
🎟️ PRIZE: FREE SEAT IN THE LYCEUM 🎟️ Pick your cohort. Technical, Business, or Creator. Your call. ---- 🇺🇸 Quick note first. This post is going up Today because we took Memorial Day off yesterday. To keep things fair, you've got until Sunday May 31st at 12:00 PM EST to submit. Same week of build time, just shifted. ---- 📋 THE CHALLENGE Build a folder-based AI researcher for a specific topic or industry. You pick the domain. This week's deliverable is one researcher folder that someone could drop into a Claude project and use as their personal research partner for whatever domain you've built it for. ---- 🎯 PICK YOUR DOMAIN The domain is yours. Pick something specific. Pick something you'd actually use. A few sparks to get you thinking: - 🏦 M&A activity in one industry (fintech, healthcare, defense) - ⚖️ Court cases in one area of law (employment, IP, immigration) - 🧬 Scientific research on one health condition or treatment - 🏘️ Real estate market dynamics in one city or asset class - 🥊 Competitive intelligence for one product category - 📜 Historical research on one period, place, or movement - 📚 Academic literature in one specific subfield - 📋 Regulatory developments in one sector - 📰 Journalism research on one beat (climate tech, AI policy, biotech funding) The more specific, the better. "Research assistant" is too broad. "M&A research analyst for early-stage fintech deals in the US and Europe" is right. ---- 🗂️ THE METHODOLOGY If this is your first comp, welcome. Here's what you need to know: This week (and every week) you're learning interpretable context methodology. Folders as architecture. Each file does one job well. Your researcher is a folder with five things: - 📄 identity.md (who the researcher is, what domain they cover) - 📐 rules.md (how they research) - 💬 examples.md (what good looks like) - 📚 reference/ (frameworks, source lists, key concepts) - 📖 README.md (how to use it)
2 likes • 20d
@Toby Iverson this looks amazing, I want to use it for Autism.
1-9 of 9
Matthew Mazur
2
11points to level up
@matthew-mazur-5170
I am a AI Novice. My other job is as an attorney. I am looking to build my skill set in AI to develop new businesses & improve my existing business.

Active 4h ago
Joined May 23, 2026
Florida
Powered by