google version of the folder structure we talked about. https://cloud.google.com/blog/products/data-analytics/how-the-open-knowledge-format-can-improve-data-sharing

Working through a long-term project with my agent (Hermes on a Mac Mini, talks through Slack right now). Right now it's just me talking to her, but as I bring in more people on the ops side, I want a real way to control who can tell her to do what, not just whoever's in the Slack channel. First piece I'm building: a permissions management UI sitting outside Slack. Before I start from scratch, curious if anyone in here has already solved this for their own setup. What did you build it on, and what would you do differently if you started over? For anyone who wants context on what I'm going to build (slowly) ---- What this is An internal tool for my own business, not a product I'm trying to sell. Alina is an AI agent running on a Mac Mini via the Hermes gateway framework, currently accessible only through Slack. This is a long-term, incremental build — roughly an hour or two a day, ongoing, no fixed deadline. Think of it the way you'd think about developing an employee: capabilities, access, and trust grow over time as Alina takes on more tasks, more integrations, and more data. The actual problem Talking to an agent purely through Slack conversation doesn't scale as a way to manage or trust it. Every instruction, every permission, every piece of context lives in scattered messages. There's no way to verify she actually did what was asked — only her own report that she did it. As she takes on more tasks, more connections, and more integrations, that gap gets worse, not better, because there's more surface area and no more visibility than before. This is a verification problem first, and a control/visibility problem second. A nice dashboard showing what she's capable of doesn't fix it if it can't also show what she actually did. The vision: a web control plane alongside Slack Not a replacement for talking to her in Slack — a second surface that gives direct visibility and control, instead of relying entirely on her self-reporting. It covers five things: Skills and jobs. What she's capable of doing, and what she's actively running or scheduled to run. Read-only visibility into her current capability set.

How is everyone hosting their business data?

https://finance.yahoo.com/technology/ai/articles/spacex-buy-cursor-ai-coding-103445855.html

Github Just released spec-kit and in a few days it has 95k stars and 8.3k forks This isn't just any project. It's GitHub telling you how to really program with AI. The problem with AI agents isn't the model It's that you send it an idea in text and it interprets whatever it wants Spec-kit solves that with 6 commands that turn your idea into a structured specification before writing a single line of code ✅ /speckit.constitution → the project's rules: quality, testing, architecture ✅ /speckit.specify → you describe WHAT to build, not the stack ✅ /speckit.clarify → the agent asks what it doesn't understand before starting ✅ /speckit.plan → now you choose the technology ✅ /speckit.tasks → list of tasks ordered by dependencies ✅ /speckit.implement → the agent builds The deliverable is no longer code generated wildly It's a living specification that your AI reads, validates, and executes step by step It works with Claude Code, Cursor, Copilot, Codex, Gemini CLI and more than 25 agents The real difference is this Before: "make me a task app" and you pray the agent doesn't get lost halfway Now: specification first, code after The agent knows exactly what to build, in what order, and why 95k stars. 8.3k forks. Published by GitHub itself. MIT license. the repo here ⬇️ https://github.com/github/spec-kit