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

Memberships

Clief Notes

27.4k members • Free

101 contributions to Clief Notes
From "Manual Hell" to a Global Partnership: My Meeting with the Head of AI
Today was a massive win. I had my meeting with the Head of AI for our global group, and it went beyond anything I had imagined. The Pitch: 132 Orders and a "Broken" System I had the chance to present a real-world challenge: Manually processing 132 sales orders in April. The workflow is a nightmare: Open each order, find the amount, cross-check it with an Excel sheet, invoice it, and repeat. To make it worse, there is a known bug in our D365 environment where the amount column simply shows "0" in the grid, meaning I can’t just export a list. It requires manual clicks. In a busy finance department, this takes days because of constant interruptions. I presented my workflow and explained how this concept isn't just for one task—it’s a framework for almost every repetitive monthly task we have. I knew from my previous Rebill Project that if I can automate the "friction," I can win back my time. The Result: Skipping the Queue When I told the Head of AI that this could turn a 3-4 day job into about 1 hour, his eyes lit up. Even though Claude Code is still stuck in corporate governance (it's currently with our CEO to decide on a global rollout), he didn't want me to wait. He immediately assigned me a Microsoft Copilot Studio license. These are highly restricted—usually, there’s a long waiting list, and if you don't use it for 30 days, you lose it. He bypassed the entire queue to get me started right away. Moving the Needle with IT To get "Copilot Cowork" talking to D365, I had to submit a technical IT ticket to enable the Model Context Protocol (MCP). I made sure to CC both the Head of AI and my own manager. The Head of AI jumped straight into the ticket with this comment: "I talked to Allan today. He has an idea to speed up a process in finance and save days of work... The use of the MCP server for this would help him very much. Open for a call if needed or any other help for the team."
3 likes • 7h
i felt your excitement at that "ground-level" insight in my body when i read that part, bro, fr congratulations you earned it man you stay hustling
Weirdness Engine
As a product designer, I see that AI pushes design towards the middle of average. Even Claude Design produces some pretty generic outputs. I realized that what we need in order to make things feel more creative is to introduce more weirdness (https://github.com/sethjenks/weirdness-engine). In order to do that well and produce outputs that are not alienating I had to define the right level of weirdness. I did some research and created a “Weirdness Engine” to produce more interesting software designs. I would love it if you all tried it out and provided critical feedback. Let me know what you make with it.
Weirdness Engine
0 likes • 11h
lol ok bud you're fucking cracked. finally got around to tweaking it for my use - i owe ya one
1 like • 10h
@Seth Jenks i made it specialize in one specific type of design im using it for, i'll be going into detail on it soon. added it to the roto and put my homies on it too 🫡
Self governing businesses?
So if I understand correctly, the Hermes agent is the Claude agent that I’m talking to in VS Code. So….. for business owners… a self governing business is the holy grail of what we’re doing here, right? A self governing company starts at VS Code and gets built brick by brick, and that’s what’s happening right now? That’s what we’re doing? And in like 6-12 months we’ll have amassed enough data and infrastructure to support that? Am I getting it?
1 like • 11h
@Ruby Sparks nah this is the mindset and why i think i excelled early. i had zero experience. no pc friends. i didnt know what "traditional" boundaries were and so i just got creative to solve issues back when claude code had just came out. and i still managed to get some crazy results. My time wasnt spent coding. it was digging through logs. building baby memory systems and orchestration layers. truly living the vibe code life. but this isn't DOING any work, it's playing and thats the distinction you need to make right now. Make sure the scope of the tools you're building will actually be necessary for the actions that you need to be executed. But obviously still play a little too. Just don't get sucked into thinking you're going far because you're going fast. That's a trap. But what do i know 🎶 im just a girrrrl in thissssss world 🎶
See behind the veil - full architecture
This took a few weeks. Not building. Training. Tweaking. Breaking. Locking. Running the same flows over and over until the architecture stopped bending. Everyone here knows ICM. What this is… is what happens when you actually live inside it long enough. Not theory. Not clean diagrams. Real load. A few things only showed up under pressure: - The moment where orchestrator wants to execute… and you don’t let it - The cost of letting workers “figure things out” vs forcing briefs to be exact - How fast token bloat creeps in when you don’t treat load surface as a constraint - The difference between a rule you wrote… and a rule you had to write three times At some point, things flipped. The system stopped feeling like something I was managing… and started feeling like something that was holding shape on its own. That’s when the real work began. What’s in here is not “a good setup”. It’s what survived: - multiple passes of weekly audits - repeated cold starts - real production friction - and a lot of “this felt right but didn’t hold” A few things I’d pay attention to if you explore it: - Where boundaries are enforced (not suggested) - What got locked into rules vs left flexible - How briefs are treated as contracts, not prompts - How little the orchestrator actually does Also interesting: The extraction itself. That process alone shows you what was structural… and what was just personal preference. → https://github.com/NFTYoginis/creator-orchestrator-template If you’re deep into ICM already, you’ll see where this goes. Curious what breaks for you — or what holds better than expected.
2 likes • 12h
@Mary Sheilag yeah im still chewing on it, but my ideas were for for you guys but i'm curious what exactly qualifies as your guys' L2 layer or if you defined it/mapped it out
1 like • 12h
@Joann B. Campo how did you guys divide the development of this up? Do you guys have privileges for users that have access? I have so many questions lol. I've been playing with the animation pipelines lately and just recently started getting into using tui's as a presentation platform and just iterating on that idea alone has been destroying my time lol. Super neat stuff you can do with it tho
From constantly reloading the wrong files to a clean CONTEXT.md
This is my first little win since deciding to go all in < 14 days ago. Trying to help busy entrepreneurs save real time by integrating AI into their businesses without the usual headache. Truth is, I started delivering for free just less than 14 days ago while my own system is still a mess (you can see the latest cleanup in the first screenshot). I had over-described everything in my CONTEXT.md file, so I just told the agent to fix and simplify it with the help of another agent that I'm training on how to actually set up these folders, thanks @Jake Van Clief It went in, cleaned it up beautifully, added token optimization rules, fixed the pipeline, and even created a redirect so it never reads the wrong files again. Feels good to see it actually optimizing itself ( with my help ) . I’m learning that it’s better to get paid while improving than to wait until everything is perfect and stay at zero. Just pivoted into paid work now which is another huge victory because daddy is huuuunryyyy. Also been overcomplicating my website, It’s not perfect neither unique yet and I’m still refining the process, but turns out shipping imperfect work is way more effective than waiting for everything to feel “ready.” I've been silently lurking, but huge thanks to this community for the vibe and inspiration. Things are already getting smoother. What about you guys? What have you built or improved since joining? Also, I’ve noticed there are some challenges and group activities going on.. in your opinion, what’s the best way to level up fast here? Anyone actively participating in the challenges? Would love to hear your wins (big or small) 👇
From constantly reloading the wrong files to a clean CONTEXT.md
0 likes • 14h
my last post has a prompt in it that'll make ur agent feel like he is jake. i explain why in the post, you don't need the entire prompt, but that prompt is composed of high level *concepts* and injects 3 mental models at once. that's why it's fire, it's modular. Use which part you need when you need it. I didn't label 'em cause i'm posting the actual skill tomorrow and i'll explain the why there but the v1 is already up go crazy king
1-10 of 101
Yucky Yuckyyyy
5
302points to level up
@yucky-yuckyyyy-6607
nvim go brrrrrr just trying to distill abstract concepts probably adding an nvim keybind as we speak

Active 38m ago
Joined Mar 17, 2026
Powered by