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

Memberships

Clief Notes

38.8k members โ€ข Free

11 contributions to Clief Notes
What deployment options to people use?
When deploying an ICM folder structure to an actual client, asking them to drop it into their claude seems reasonable for us techy people, but some of my clients are not technical enough to even do that. What other options are people using? I'm a traditional web app guy, so deploying a cloudflare worker with some backend code and a database etc is what I would traditionally try and do. That model is not as clear cut as a winner as it used to be! Is it time to look at agentic systems to be able to deploy ICM so my clients can actually use it in their day to day? Or do we simply train them up to use claude? Or is there something else that people are doing?
2 likes โ€ข 4d
@Mark Gubuan Agree, and if possible go to their offices and implement that, I think you will get more ideas on how to improve what you do for the clients, and improve the process of implementing, learingin where people get stuck or frustrated
0 likes โ€ข 4d
@Lake Mark just for personal use, I think the way to monetize right now is through consulting, or making something for the public but then again the API costs. It sounds that you already have a great business model, I would just say start by the simple, is like Jake has been saying, try to sistematize your workflow, are you doing that business alone or do you have a team?
Have not written a proper article in a while, I changed that today.
This will tell you a lot about the future and the way I think, give it a read if you have time. https://jakevanclief.substack.com/p/the-machine-is-smart
0 likes โ€ข 4d
So, imagination, creativity, logic, and critical thinking will become some of the most valuable assets of the future.
๐Ÿ† WEEKLY COMP #7: THE OPERATOR ๐Ÿ†
๐ŸŽŸ๏ธ PRIZE: FREE SEAT IN THE LYCEUM ๐ŸŽŸ๏ธ Pick your cohort. Technical, Business, or Creator. Your call. ---- ๐Ÿ‡ฌ๐Ÿ‡ง We're back. Good morning from London. ๐Ÿ‘‹ Thanks for the patience last week. Jake and I needed a few days to breathe before London Tech Week kicked off, and you all responded with nothing but support. We don't take that for granted. Now let's get back to building. ---- ๐Ÿ“‹ THE CHALLENGE Build a folder-based AI operator that handles ONE operational workflow end-to-end. You pick the workflow. This week's deliverable is one operator folder that someone could drop into a Claude project and use to handle a real business workflow without babysitting. ---- ๐ŸŽฏ PICK YOUR WORKFLOW The workflow is yours. Pick something specific. Pick something you'd actually use. A few sparks to get you thinking: - ๐ŸŽซ Customer support triage (which tier handles this ticket?) - โœ… Content review and approval - ๐Ÿ“จ Lead intake and qualification - ๐Ÿ’ธ Refund request handler - ๐Ÿค Partnership pitch evaluator - ๐ŸŽ™๏ธ Podcast guest pitch sorter - ๐Ÿ’ผ Freelance project intake - ๐Ÿ“„ Resume screen for one specific role - ๐Ÿ“… Meeting request triage (book, decline, delegate) The more specific, the better. "Customer support" is too broad. "Refund request triage for an ecommerce store doing under 200 orders per month" is right. ๐Ÿ“Ž If you want a fully written client brief as a reference, the attached PDF walks through one example. Don't build the example. Use it as a template for how to think about scoping your own operator. ---- ๐Ÿ—‚๏ธ 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 operator is a folder with five things: - ๐Ÿ“„ identity.md (who the operator is and what workflow they own) - ๐Ÿ“ rules.md (the decision logic: criteria, edge cases, escalation rules) - ๐Ÿ’ฌ examples.md (decisions in action, including at least one edge case) - ๐Ÿ“š reference/ (checklists, templates, rubrics) - ๐Ÿ“– README.md (how to use it)
5 likes โ€ข 5d
Hi All: This is my late entry, not really for the comp, but more about complying with myself and keep building. Life happens and sometimes you can't keep up, but I wanted to deliver my week's work. This is an integration of different things I've been developing, most of the within the competitions: a full multi-agent system where you pitch an idea and get a working, deployable solution. It starts with a chat to define the idea, goal, users, style. The agent gathers context until it has a clear picture, then you tell it to carry out the rest without supervision. From there it moves through a research phase, process definition, design, ICM building, UI design, code generation, and finally an audit. If major issues are found it loops back to fix them. When it's clean, you get a deploy message. Every stage is documented. Handoffs are explicit. Agents know what was done before they touch anything. A local dashboard lets you track the whole pipeline in real time, inspect the visual design system, and read or edit the ICM instructions at any stage. To test it I asked it to build a personal training system for bouldering progression. It came back solid, requirements met, deployed, no major bugs. This was the first test, want to test it further with more complex systems, I have tested the developing part with other projects seems to work good. I'd like to improve the visual design and to test it with more complex requirements. If someone finds it useful or have any suggestions it would be cool. For me, this one works best in VS Code or Cursor. Open the full folder and you can create a solution from there. Repo: https://github.com/Virgiliorobor/solution_creat Landing page: https://soland.virgiliorobinson.com/
๐Ÿ† WEEKLY COMP #6: THE RESEARCHER ๐Ÿ†
๐ŸŽŸ๏ธ PRIZE: FREE SEAT IN THE LYCEUM ๐ŸŽŸ๏ธ Pick your cohort. Technical, Business, or Creator. Your call. ---- ๐Ÿ‡บ๐Ÿ‡ธ 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. ---- ๐Ÿ“‹ 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. ---- ๐ŸŽฏ PICK YOUR DOMAIN The domain is yours. Pick something specific. Pick something you'd actually use. A few sparks to get you thinking: - ๐Ÿฆ M&A activity in one industry (fintech, healthcare, defense) - โš–๏ธ Court cases in one area of law (employment, IP, immigration) - ๐Ÿงฌ Scientific research on one health condition or treatment - ๐Ÿ˜๏ธ Real estate market dynamics in one city or asset class - ๐ŸฅŠ Competitive intelligence for one product category - ๐Ÿ“œ Historical research on one period, place, or movement - ๐Ÿ“š Academic literature in one specific subfield - ๐Ÿ“‹ Regulatory developments in one sector - ๐Ÿ“ฐ 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. ---- ๐Ÿ—‚๏ธ 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: - ๐Ÿ“„ identity.md (who the researcher is, what domain they cover) - ๐Ÿ“ rules.md (how they research) - ๐Ÿ’ฌ examples.md (what good looks like) - ๐Ÿ“š reference/ (frameworks, source lists, key concepts) - ๐Ÿ“– README.md (how to use it)
0 likes โ€ข 19d
If you are curious about what hts is, here is a short video generated with Gemini that explain:
1 like โ€ข 19d
I am sharing this in case it pushes someone else to build within the comp framework. This weekโ€™s entry was not really for the challenge or the comp. I am already fortunate to have my seat at Lyceum, so this was more about keeping momentum and continuing to build. I focused on a problem from my regular workflow, something I had tried before and failed. This time, using ICM, I was able to narrow the sources, design the thinking process, add rules, and give the model a specific space for interpretation. That changed everything. Before, the agent searched the web too broadly and produced weak results. This time, the output was genuinely useful. It is token intensive, around $3 to $5 per item researched, but compared with a regular classification opinion that may take several hours, it still makes sense as an internal support tool. What impressed me most was not only the result, but realizing that these challenges are building a real muscle. I am understanding more, deploying more, and solving problems I could not solve before. The funny part is that a good part of this was done from my phone, instead of scrolling IG or X. So if you are thinking about building something for these challenges, do it. Submit something. You are not really competing with anybody. You are improving yourself.
๐Ÿ† WEEKLY COMP #3: THE SPECIALIST ๐Ÿ†
๐Ÿ’ฐ $325 CASH PRIZE ๐Ÿ’ฐ That's a full year of Premium. Win this and your membership pays for itself. ๐Ÿ“‹ THE CHALLENGE You just got hired again. Different client this time. Meet Sarah, a freelance copywriter who's drowning in context-switching. ๐Ÿ“Ž Download the full client brief attached to this post. Short version: She works with three types of clients (SaaS founders, ecommerce brands, local service businesses) and starts from scratch every project. She doesn't need another tool. She needs a system. Your job is to build her a folder-based AI specialist she can drop into any Claude project. The folder IS the deliverable. ๐Ÿ—‚๏ธ THIS WEEK YOU LEARN ICM Up until now, comps have been "build a thing." This week you utilize the methodology taught throughout the community. ๐Ÿง  Folders as architecture. That's it. That's the whole concept this week. Your specialist is a folder with five things: - ๐Ÿ“„ identity.md (who they are) - ๐Ÿ“ rules.md (how they respond) - ๐Ÿ’ฌ examples.md (what good looks like) - ๐Ÿ“š reference/ (source material) - ๐Ÿ“– README.md (how to use it) Drop the folder into a Claude project. Claude becomes the specialist. Reusable. Shareable. Portable. ๐ŸŽฏ PICK YOUR SPECIALIST Don't pick copywriting. That's Sarah's example. Pick something YOU would actually use. A few sparks to get you thinking: - A salary negotiation coach - A meal planner that knows your dietary restrictions - A code reviewer for your stack - A real estate market analyst for your city - A technical recruiter screener - A grant writer for nonprofits in your space The more specific, the better. "Marketing expert" is not a specialist. "B2B email expert for enterprise SaaS targeting CFOs" is. ๐Ÿ’ผ WHY THIS ONE LANDS ON YOUR RESUME Real talk. Winning a comp in a Skool community doesn't get you a job by itself. But shipping a working folder-based AI specialist with a clean README and a public repo? That's a portfolio piece.
1 like โ€ข May 18
Hey @Andrew Carter sorry for my late reply! It was mostly HTML/CSS and Claude Python. My idea was to create tables that could then become the MD files. For Comp 4, I tried to use this to build the multi-agent setup, but I had a hard time with the handoff and mapping. I had to keep things closer together, so I ended up making the other parts manually and adjusted this project along the way. Iโ€™ll try again during this week to make the system work as a multi-agent setup, because I think this could be a good starting point for other projects.
1 like โ€ข 19d
@Giovanni Garcia Hi! not at all, netlify credits, but I am switching everything to my server, it will be available in a couple of days, I will let you know
1-10 of 11
@virgilio-robinson-1247
Trade and Customs specialist trying to implement AI and Tech

Online now
Joined Mar 11, 2026
guadalajara, jalisco
Powered by