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

Owned by Jim

Build It Right

4 members • $47

Get your AI work out of scattered chats and into a workspace you own, then build real things with it. Run by a dev with 13 years shipping software.

Clief Notes

45.9k members • Free

Build Market Close

328 members • Free

Skoolers

161.9k members • Free

AI Automation Society

440.7k members • Free

Claude for Coaches

1.6k members • $47

Lifestyle Founders Group™

13.5k members • Free

123 contributions to Clief Notes
I'm giving away my OS map. The map was never the moat.
You built an agentic OS. So did the person three seats over. And when you put your architecture next to theirs, the shapes rhyme. Folders for clients. A governing layer up top. Named agents doing scoped work. An orchestrator routing it all. That's not a coincidence and it's not theft. It's convergence. Builders with no access to my internal architecture keep arriving at doctrine I already wrote down. One builder reasons their way to belief over prompting. Another builder names an agent and discovers that's the hook for giving it a soul. And another builds a routing gate to protect the signal. Different vantages, same destination. None of them copied me. They solved the same problem in their own org and ended up in the same place. I used to find that mildly surprising. Not anymore. Because if a stranger reinvents the doctrine without ever seeing it, the doctrine isn't clever positioning I invented. It's just how this actually works. Convergence is the proof that it's true. Which tells me the map was never the moat. If people can rebuild a system from a screenshot of a folder tree, then handing over the clean version costs me nothing and proves the point. So here it is. An outline of the AgencyOS map is attached to this post. Layers, agent roster, sample folder structure, and tool integrations. Take the shape. Start at Layer 1, not Layer 3. The agents are the fun part, so that's where everyone wants to start. The leverage is upstream. The belief layer governs everything the agents produce. Mine didn't come from a build sprint. It started forming in late 2023, with these ideas spoken aloud on a podcast, before any AI was in the picture. Then I spent over a year encoding that conviction into a system. Then I found ICM and ported it over. I'm still refining it. An agent I can spin up in 15 minutes. The belief layer took years because it had to exist before the machine did. Build the workforce on top of nothing and you get a fast machine with no conviction. And the belief layer is the one thing on that map you can't take from me. I can't take yours from you. You can copy the folders. You can copy the agent names. But you cannot copy what I believe into your system. I can go into my AI and ask it "what do I believe?" and it returns my truth. If you load my doctrine and ask the same question, you get what I believe. Not what YOU believe.
1 like • 6h
Grabbed the map when you posted it and finally sat with it properly this week. Good bones. My build didn't converge with yours though, and I think the reason matters. Mine came out knowledge base shaped, mostly because it started as one. Before any of the rest existed it was a wiki where I captured what I trusted from people ahead of me, subject by subject, with a charter on top. Client work arrived later and slotted in as its own layer without taking the place over. The coding projects carry their own rules inside their own folders. The knowledge base stayed the center. I do have workflows, but they live out at the edges as skills sitting next to the work they run. Nothing workflow-shaped made it into the governing layer. Your map reads the opposite way to me, the pipeline right under the belief layer and everything serving it. So maybe some of the convergence you're seeing is origin rhyming with origin. Systems born doing client throughput grow a pipeline spine. Mine was born as a library, and everything since has had to fit around the library. Your Layer 1 point survived the different shape though, and that's the interesting part. I read the Worldview Engineering piece before commenting. Your dig site was your archive. Seventy-five episodes and a decade of client calls, and the AI surfaced doctrine you'd been enforcing without naming it. I didn't have an archive like that. Mine surfaced from logging every spot I rewrote what the AI drafted before I'd let it go out under my name. Each rewrite is a belief showing itself. A few months of those logs and the system answers "what do I believe" in my words, with receipts. Same excavation, different ground. Yours needs a back catalog. Mine only needs you to keep catching the machine being slightly wrong about you, which also means I couldn't have done the belief work before turning the machine on. Half of mine only exists because the machine ran first. Curious if anyone else building off the map ended up with their center of gravity somewhere other than the pipeline, or if I'm the outlier here.
Who here is building a company?
I am interested in connecting with other founders. I've connected with a few, but I suspect there are a few more hiding in here. To get the conversation going, can you share: - What company are you building? - What founder problem are you dealing with right now that ICM can't solve for you?
1 like • 14h
@Leonard Dauksza I do have the company spun up but I am currently working on taking a couple clients across the finish line. Real projects and finding the similarities across them is my focus at the moment, so trading my time for money and research/references. I am less focused on what the scalable product is until I implement for a couple clients. The company I consulted for took over a whole market that way. They kept doing similar things on every project then built a COTS system that was customizable and took over the space where even big names were failing projects. This is not as sexy as a video of boom copy this and sell 5K-20K engagements on this simple process /link in bio BS.
First audit
First paid-path audit tomorrow — talk me through it? Tomorrow I run my first automation audit for a medical/behavioral health billing company. Free audit, paid build after — that's the deal. Setup so far: Pre-call email sent (tools list, screenshots, one real failure example) Client is recording Looms of the broken automations, narrating the "why" while clicking Zoom cloud recording on → transcript drops into 00_capture → workflow-map after One thing that's got my attention: they've worked with AI companies before, and those companies shut down. So I'm walking into a client who's been burned. Questions for anyone who's done a first client audit: What do you wish you'd asked on call #1? How do you handle a client who's skeptical because the last AI vendor disappeared? Anything you'd add to the 60/30/10 gut-check when auditing billing work specifically? Will report back after the call.
2 likes • 14h
The main thing for me in consulting especially in a first engagement is to focus on listening, over pitching. Getting that deep understanding of their pain points and the structure you are walking into is the number one focus. It is easy to have a pre conceived notion of how their process should work, then try to force it into one of your design patterns. Gather info then come back with a proposal after you have fully digested their situation. Off the cuff solutions can bite you. Trust is the biggest thing. Every new client I have started with in my consulting world is skeptical, they have often been burned in the past. Earn their trust by underpromising and overdelivering. Good luck with this engagement. The part I like is two years into a project when they finally trust me and will not fight back against my advice, even if goes against how they have done it forever. 😂
The Lyceum
Anyone else getting pumped? I know I am. Mission Control setup and ready for countdown
The Lyceum
0 likes • 1d
@Dino Behler That is one nice command center there
2 likes • 1d
@Jordan Shaw beep...boop...how are you liking the community? 🤖
Client needs some devs/workers
I have a client in Australia who's looking for someone who understands ICM and can help him work on his software. Obviously he would prefer someone a bit more technical, but he's happy to have some people who are trying to learn as well. It's a pretty large software, but he's created a pretty good automated system and obviously he's using my methods so it's very well organized. Anyone out here looking for a project to take on the practice or learn more? Or is there anyone in the morning to get a little bit more work done at a higher level? He's looking for multiple skill levels.
3 likes • 2d
There it is the use case for the Eduba Ledger job board. Australia time is perfect EST evenings and their morning
1-10 of 123
Jim Tyndall
5
142 points to level up
@jim-tyndall-3250
13 years shipping production software. I build with AI weekly for real clients, and I care most about the questions the AI never volunteers.

Active 4h ago
Joined Aug 16, 2026
Northeast USA
Powered by