I wrote an article about why you should use ADRs and what they are. It's a simple read, maybe like five minutes. https://kuality.design/en/blog/why-solo-developers-need-architectural-decision-records-adrs

how do you implement ICM safely in a team! I'd love to get this across my organisation but I'm concerned about permissions and access to information. I'm leading the organisation - what I have access to far supersedes what my team should have access to (client details, pricing, methodologies, etc). And how do I protect all of this leaving with staff if they move jobs etc? I mean the better we build these systems, the more of our secret sauce gets encapsulated, right?

So, if you’re looking to set up a memory system but with all the new obsidian, graph, this and that sort of AI news, you just don’t know which one to, here’s what I recommend. I don't know your exact use case so I recommend copy pasting my message, putting it into claude and talking to it about your use case. So you have the obsidian stack, where the AI first looks for a topic, it doesn't exactly ask (query) any sort of external system. How it works is that the AI has a sort of index page, you know how our school text books have those main pages with chapters and page numbers? Something similar, but in this case, every "Chapter" leads to another chapter which is related to the main topic. So let's say you have a topic such as "How do I implement the apple branding guidelines", it would find that first, then it would see that there's a reference of another page, such as "How to implement a luxurious design with react", both relevant so far, now inside of the how to doc, it would refer to "How to save tokens while designing a website", now Opus could possibly think of saving tokens but by default with just the most simple prompt and topic you gave it, it would not go to that doc, it pulls the first 2 relevant documents and then understands that. If you're wondering how you even get those docs, you basically dump your notes, research papers, whatever you'd like to and then it would use AI to sort it out, 1 research paper can become 50-500 different documents, this is the Andrej Karpathy memory system. https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f The 2nd method would be through Vector, it's not always needed though. Going into Vector, it query's your database but with an unclear task. SQL would be: "find users where plan = paid" You know exactly what you need and need definitive results. Vector's more like: "find docs similar to this concept"

Hey folks, wanted to get your input on something. I've ventured into so many things over the years only to realize after hours of work that the particular framework or some specific methodology won't work for my use case. Seems this is the natural way of software: subtle differences you don't realize matter until you're neck deep and hours in. SO, here's my question: Who is this framework NOT for? Is there any type of person or use case that will get into what @Jake Van Clief has generously put together here and go, "Eh, that just doesn't work for my situation?" And who is that? Thanks in advance!

A friend of ours @Joseph Fioramonti built a tool called Constellations (If you have a watch or attended the first ever afternoon tea session. You'll know who I'm talking about). It measures something most people and most companies get wrong: the gap between what you think you respond to and what you actually respond to. Take it here 👇(also I am NOT getting paid for this and this is not some sponsored thing. Joe does really cool work) https://gen.constellations.app/constellations/survey/d269cab5-coca-cola/skool 📋 How it works: You'll see a grid of Coca-Cola images across two pages. Drag the green (+) dots to the images that make you want a Coke right now. Drag the red (-) dots to the ones that don't. Hit submit. That's it. 🧠 Why this matters: Every day we interact with systems that run on words. Search engines, AI tools, prompts, interfaces. The words we use are becoming instructions. They're becoming code. But here's the problem. If someone asks you "what kind of marketing works on you?" you'll give an answer. And that answer will be mostly wrong. Because desire and language live in different places. You feel a response to an image before you can explain it. You scroll past something or stop on something before your brain catches up with a reason. Constellations measures that gap. The space between what you say you want and what you actually respond to. This is the same problem companies spend millions trying to solve. It's the same problem you'll run into when you build anything that depends on understanding what people actually care about. And it's the kind of thinking that separates people who build things that work from people who build things that look right on paper. Take the survey. @Joseph Fioramonti will compile the results And provide a report shortly! He is an expert in branding and psychology and can come up with some really amazing reports.