Activity
Mon
Wed
Fri
Sun
Dec
Jan
Feb
Mar
Apr
May
Jun
Jul
Aug
Sep
Oct
Nov
What is this?
Less
More
79 contributions to Clief Notes
🏆 WEEKLY COMP #16: THE SIMULATOR 🏆
🎁 $1,000 IN PLATFORM CREDITS 🎁 One winner takes it. 📋 THE CHALLENGE Build a folder that plays one specific person, so someone can practice a hard conversation before the real one. Drop the folder into a Claude project and Claude becomes that person. The user pitches, negotiates, interviews, or delivers the bad news. The persona reacts the way the real person would. This week's deliverable is one simulator folder someone could use tonight to rehearse tomorrow's meeting. 🎯 PICK YOUR PERSONA Pick someone people dread talking to. Pick someone you have sat across from. A few sparks: - 💼 A skeptical Series A investor at a healthcare-focused fund - 👔 A hostile hiring manager for a senior engineering role - 💰 A client trying to talk your rate down - 😐 A defensive employee getting hard performance feedback - 🤝 A possible cofounder testing whether you'll last - 📞 A cold prospect who picked up the phone and wants off it - 🎤 A journalist working on a critical story about your company - 🏠 A landlord who doesn't want to fix the thing - 📋 A grant reviewer with a strong view of what counts as impact The more specific, the better. "A tough boss" could be anyone. "A CFO at a Series B SaaS company who has been burned by two failed marketing hires and now questions every dollar" is one person. 🔥 THE ANGLE THIS WEEK The last five comps were heavy. Cite every line. Check against a rule. Hold a shape. Prove the folder helps. Rebuild against your feedback. This one is lighter to build and just as hard to get right. The Rebuild asked you to take hard feedback and act on it. The Simulator gives people a place to practice that before it counts. A simulator earns its keep by staying in character when it would be easier to break. Three things make a persona hold: 1. It wants something. The investor wants a 10x return and a founder who knows their numbers. The hiring manager wants to fill the seat without a mistake. Write the goal in identity.md. Every reaction comes from it.
5 likes • 4d
https://github.com/BlkAdder72/Disconnect-Dojo It felt like it took forever for me to cancel my internet service, and after one more question and one more offer, I almost kept it just to get off the phone. I built Disconnect Dojo so you can practice canceling in your own words with Darren Pike, the retention rep who wants his bonus. For fun, I created some additional personas for Darren to make the interaction more interesting. To try one of Darren's optional personas, send one of these mode names as the entire first message in a fresh Claude Project chat: Deadpool Mode, Don Rickles Mode, Larry David Mode, Lewis Black Mode, or Steven Wright Mode.
Are MD Files dead?
I just saw a YouTube video that discussed the death of MD Files, arguing that HTML files are the better way to go. Wanted to get the community ‘s thoughts on this and how it would impact ICM approach, if at all. Thanks
Are MD Files dead?
1 like • 15d
Here is some reference articles referenced in video and in research on this issue to further discussion. https://infoq.com/news/2026/06/anthropic-html-markdown-agent https://noqta.tn/en/news/anthropic-thariq-html-over-markdown-ai-outputs-2026 https://www.thurrott.com/a-i/335933/anthropic-engineer-debates-use-of-markdown-vs-html
2 likes • 14d
@David Vogel thanks, will review. Clearly YouTube is way behind this community!
I was sure switching AIs was the smart move... 300 reviews later, I'm not.
Last week I posted part one of Second Eyes (https://www.skool.com/cliefnotes/i-expected-a-second-ai-from-another-company-to-catch-more-it-caught-less?p=4179abfc. Quick recap... I planted 288 mistakes in 12 renovation cost estimates and had Claude, ChatGPT and Gemini review them in the browser, 180 reviews in all. A second AI from a different company didn't catch more than a second Claude. Two Claude reviews caught 84%, and Claude plus another company caught about 82%. A few of you asked the obvious next question. What about the tools people actually use? So I tested mine. WHY THIS ONE My everyday setup is Claude Code for the work and Perplexity as my second set of eyes. Claude Code is the version of Claude that can write and run code, so it can recompute every number instead of reading it. Perplexity picks the model for you and can search the web. If any setup was going to beat "ask Claude twice," I figured it would be this one. WHAT I DID Same 12 sheets, same 288 mistakes, same prompt and answer key as part one. Claude Code reviewed every sheet 5 times with all my personal settings switched off. Perplexity reviewed every sheet 5 times in incognito on its "Best" setting. That's 120 reviews, all on the same day. Before any data came in, I wrote down what would count as a win. Perplexity as the second look had to catch at least 5 points more than a second Claude Code review. WHAT CAME BACK Claude Code plus Perplexity caught 83.8% of the mistakes. Claude Code plus Claude Code caught 83.2%. Half a point. The 5-point gain is ruled out. On its own, Perplexity caught about 72% and Claude Code about 77%. And Claude Code caught about the same as the regular Claude chat from part one, 77% against 79%, even though it ran Python on every single sheet. The part I found most interesting... Perplexity and Claude miss different things. Perplexity was better at catching work done in the wrong order. It was much worse at catching numbers that contradict each other across the sheet, and claims that weren't true. But when I paired them, those differences mostly cancelled out. A second Claude Code review picked up about as many new mistakes as Perplexity did.
I was sure switching AIs was the smart move... 300 reviews later, I'm not.
1 like • 15d
I just started using a legal AI harness that allows you to use up to three separate models to answer a legal prompt or document evidence etc. you can use different levels of Claude or chat etc. To be clear they are run at the same time and you can see their analysis going at the same time and a collated result is provided. What I found interesting is that they used your originally chosen model to collect their findings and determine where they agree and diverge. The result was extremely powerful for my legal related use case. The reason I bring it up is could a similar approach in your use case make it better. Each models reviews rolled into a master review and then a final review performed based upon the results looking for anything that was missed.
I Built a Mutual NDA Template for AI Collaboration. Now I'd Like Your Feedback.
After dealing with some rather restrictive NDA terms during a potential business collaboration, I started wondering: Why should protecting your ideas, projects and intellectual property be so complicated? Especially now that we're collaborating with AI agents, sharing Git repositories, developing software together and potentially turning projects into businesses. So I decided to put together something practical. NDA-UNIVERSAL-001 · Version 2.2 An English-language mutual NDA and non-use agreement, designed to protect both parties fairly. It covers: - Confidentiality and protection of existing intellectual property. - Independent development without unnecessary non-compete restrictions. - AI agents, external models and data processing. - GDPR and relevant US privacy considerations. - Git repositories, shared code and collaborative development. - Clear separation between access, collaboration and commercial exploitation. - Ownership of contributions and separately agreed commercial rights. I've also included a plain-English explanation for people who aren't lawyers, plus an ICM-compatible Markdown structure for AI-assisted workflows. Here's what I'd like to do next. Rather than keeping this as my own document, I'd love to explore turning it into a community-maintained standard. A version-controlled template where people can suggest improvements, identify unfair clauses and contribute practical experience. And ideally, have qualified legal professionals review it. Important: This is currently a draft based on German law, not a legally certified or universally enforceable agreement. The international aspects especially need professional review. I'm not looking for blind approval. I'm looking for constructive criticism. If something is missing, potentially unfair or legally questionable, let's identify it and improve it. And if anyone here is a lawyer, works with contracts or knows someone who might be interested in reviewing this, I'd genuinely appreciate the input.
0 likes • 15d
It is a good concept, but you must be careful as in some jurisdictions providing legal advice without being a licensed attorney is against the law. That being said you would need to make sure that you have visible disclaimers that this is a diy tool, not legal advice and recommend that the user should seek legal advice. In the States unauthorized practice of law is taken seriously and state bar associations do prosecute claims. So you need to do research on how to thread the needle to avoid the issue. My Disclaimer: this is not legal advice, this is for educational purposes only. I am not your attorney.
📣FREE Tool: Visualize your folder context for a given task
I've been quiet lately between personal projects/lyceum/day job and life with family and friends. Rest assured, I am still working. Had this idea this morning to make a tool for folks to visually audit your ICM workflows in the order that the agent reads files for a given task. Turned it into a skill for everyone here. https://github.com/donroy26/workflow-tracer Invoke the skill for a given folder and write the task you want and the agent will give you a dashboard like shown in the attached photo. You can then audit all the files it walks for that task and see if any wires are crossed. Let me know what you think!
📣FREE Tool: Visualize your folder context for a given task
0 likes • 16d
Thanks for sharing, great idea!!
1-10 of 79
Matthew Mazur
5
249 points 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 3h ago
Joined Jun 25, 2026
Florida
Powered by