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

38.7k members โ€ข Free

4 contributions to Clief Notes
WEEK 7 COMPโš™๏ธ THE OPERATOR โ€” RESULTS
(and a small change to how we run these) Hello everyone!! ๐Ÿ‘‹ First, the honest bit. This one is landing later than Monday, and on purpose. Two things got us here. One, a lot more of you are submitting now. If I am going to really sit with every entry and give it a proper look, a weekend is not enough. This round I went through all of them, watched the videos, opened the repos, the full pass. That takes time and I would rather do it right than rush it. Two, I could feel a few of you running hot. Weekly is a sprint, and burnout was starting to creep in for some. So we are moving to bi-weekly. More room to build, more room to breathe, and the time for me to actually review the work the way it deserves. ๐ŸŽฅ Quick word on the videos. They were a step up this round. Some of the animated walkthroughs and live demos were a genuine pleasure to watch, and yes, I weigh them. A clean demo that shows the thing actually working makes a real difference. However I don't want that to ALWAYS be a requirement. Also you will notice the Heavy hitters that you usually see up here are not currently, some posted late and I decided to let the new entries and first timers also have a chance as well! But certainly, check the original post as every submission has something for you to learn from : ๐Ÿ’ฐ Competition 7 โž–โž–โž– ๐Ÿ› ๏ธ A FEW THAT STOOD OUT (in no order, and if you didn't make it, it doesn't mean yours wasn't great) The Pipeline Operator โ€” @Jayden Forshee Runs a whole sales pipeline. Paste a lead and it grades it, writes the outreach, and moves the card itself. The live board where you watch cards move on their own, sat right next to a normal chatbot, was one of the clearest ways anyone has shown what an operator actually is. https://github.com/griffainai/studio-pipeline-operator Board: https://pipeline-operator.vercel.app/board
3 likes โ€ข 11h
Congratulations @Gabriel Azoulay ! Nightwatch is amazing! The business-impact judgment piece really clicked for me. Congrats to everyone who built and submitted. The range in this round is honestly inspiring! And thank you @Jake Van Clief for the shout-out on job-fit. This honestly made me emotional. It was my first time submitting, and for me, the real win was posting at all. I put my work out there before it felt perfect, and I got past the fear of not being โ€œgood enoughโ€ yet.
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)
4 likes โ€ข 6d
WEEKLY COMP #7 SUBMISSION An adversarial job-fit operator. It will not tell you if you will get the job. Nothing can. It cannot know the room. It tells you where you are likely to get screened out and what you can fix before you apply. Paste one JD and one resume. Get: Apply / Apply with Caution / Do Not Apply The gate most likely to screen you out The evidence gaps and likely objections Resume signals to strengthen A first outreach message already drafted It owns one decision: Is this specific role worth pursuing? I had been circling this problem long before the contest, testing fit checks against my own applications. I have burned weekends tailoring for roles where the rejection was probably visible before I hit submit, and I have talked myself out of roles I should have pursued. The contest brief did not give me the idea. It gave me the deadline. You can already paste a JD into Claude and ask for a fit check. So I did not build that. Ask raw Claude to rate you three times and you will usually get three numbers, all a little too generous, because a chat wants the conversation to go well. Here, Claude only labels the evidence. Code computes the verdict. The model cannot talk its way past the rules, and every report ships with a Score Receipt you can recompute by hand. Two commitments shaped the build: First, the model cannot pick the number. Claude labels each requirement: required vs. preferred, core vs. peripheral, met vs. missing, obtainable vs. hard prerequisite. Plain JavaScript computes the score, verdict, and recommendation. The skeptical-committee voice writes the narrative, but it has no channel into the math. Second, the tool has to be usable in a browser right now. Load Demo needs no key. Or bring your own Anthropic key: it stays in your browser and goes straight to Anthropic. Pasted JDs and model output are treated as untrusted input, not executable content. It is still a static BYOK demo, so for safest use, run the no-key sample or use a low-limit key.
My dad died when I was 15. Today is his birthday.
***A note before you read: this post talks about losing a parent to drug overdose, addiction, and some of the harder parts of growing up through that. If any of this hits close to home, take care of yourself first.*** This is personal, not ai related but feel its important to share. Both @Matthew Creamer and I lost our fathers to drug overdoses. I don't say that for sympathy. I say it because it's the kind of thing that rewires your entire life and I think some of you need to hear that the people building this thing with you know what it feels like to start from somewhere broken. My dad was a good man. I need you to know that before anything else. He was loving, he was present, he was the kind of father who wanted his son to never have to grind through the kind of work he did. He spent his life in construction, the kind that wears your body down year after year, and he always told me he wanted something different for me. He wanted to retire the whole family one day. He wanted to leave a mark on the world and he wanted me to do the same. He just had his demons, and one night when I was 15 they took him from me. A month after my birthday so I was still basically 14 years old and I found him on the couch and that was it. Everything after that moment I had to figure out on my own. I learned how to trim my beard without him standing behind me in the mirror. I learned how to haggle with taxi drivers in countries he never got to see. I broke my heart for the first time and had nobody to call who could tell me what that kind of pain actually means when you're young and don't know who you are yet. I fell into addiction myself somehow escaped after a lot of battles. I joined the Marine Corps and that brought its own tragedies, its own weight. I climbed the tallest mountain in Europe. I walked across the grand sands of the Middle East. I have tasted war and peace, depression and anger, and so much more that I am still learning how to carry.
My dad died when I was 15. Today is his birthday.
0 likes โ€ข Mar 13
Thinking of you today, Jake. Thank you for trusting us with something so personal ๐Ÿ’™
Who's here? Drop your intro.
Tell us three things: 1. What you do (job, industry, student, career-changer, whatever) 2. What brought you to Clief Notes 3. One thing you're trying to figure out right now related to computing or AI I'll respond to every single one. And read each other's intros too because the person who's stuck on the same problem as you might already be in this thread. I'll go first I am Jake, I have been working in tech for 15 Years, building with Generative AI for 3 Years straight now! Excited to teach and learn! That's it. Simple, scannable, gives you data on who's joining and what they need, and keeps the feed clear for content that retains people past week one.
0 likes โ€ข Mar 10
Hi! Iโ€™m Jodi. Iโ€™m a product designer who has spent the last several years working on complex enterprise platforms. Over the past year Iโ€™ve also been working on AI-assisted workflows and AI personas for education. I joined Clief Notes after seeing Jake's Instagram post about file structure vs. agent-heavy systems. A mentor had mentioned something similar months ago, and Jakeโ€™s explanation made the idea click. As a designer, Iโ€™m fascinated by how knowledge structure and context shape AI behavior - the rules, guardrails, and interaction patterns that determine how these systems actually act for users. Iโ€™m here to understand the architecture behind that layer.
1-4 of 4
Jodi Paige-Lee
2
13points to level up
@jodi-paige-lee-5859
Designer focused on human-AI interaction. Here to learn how intelligent systems are built.

Active 2h ago
Joined Mar 10, 2026
Powered by