Two hours, live, building a company brain from scratch with Austin Distel. Your AI does not have a capability problem. It has a context problem. A company brain is plain files in a folder your team already owns, read by an AI that knows how to route a question to the right one. The folder we handed out and the prompt that runs the setup are both on the same page here: https://os.agenticsociety.com/company-brain To connect with Austin directly: AgenticSociety.com/meet For those who want join the online Agentic Society membership to join our next 90 day sprint, details and links to pricing and how to join can be found here: https://agenticsociety.com/pricing If you have questions about joining this level, online or in-person in Austin, TX, feel free to send me a direct message here on Skool or email: [email protected] CHAPTERS 00:00 Welcome, and how the two of us got here 03:00 The thesis: a business that thinks for itself 05:00 Own your data, stay model-agnostic 07:00 Hire your AI the way you hire a person 10:00 The tooling floor, and what it costs 12:00 Why build a company brain: the six reasons 16:00 Rot and drift, the two ways AI memory fails 18:00 V1, V2, V3: you, your team, your agents 20:00 Security, HIPAA, access and governance 21:00 Shared Drive, not My Drive, and why 25:00 What to gather first 27:00 Inside the structure: CLAUDE.md, markdown, the inbox 29:00 Demo: the bookkeeper run 31:00 How the brain onboards itself 33:00 Permissions in practice 35:00 Employee onboarding as the design spec 36:00 The HR director hack 40:00 soul.md, CLAUDE.md, and a chief of staff named Riff 45:00 The daily close, and the mistakes log 48:00 Evergreen versus ever-growing context 53:00 Version control and change logs 56:00 Demo: asking a live brain for the vacation policy 1:03:00 Demo: the starter prompt and the harvest

Hey all - the summer schedule June-August will be limited down to one bootcamp end of June or early July, date TBD. The official date of the bootcamp will be announced here first and we will have some sort of members mastermind around that time too. In part this decision was made for health, and both personal & professional reasons. One important one I am sharing with you right now, is that I am now working with Agentic Society officially as their fractional Chief Agent Officer. I'll be working directly with Austin Distel and the internal team to build out product to work directly with my good friend and founder of Agentic Society to support product development for members and clients - specifically with the next 90 days being a big part of building and shaping the product. I plan to continue monthly bootcamp/workshops as we continue to improve the format for the AICOS plugin and workshop series which is available now for GenAIU Premium members. And I'll say- Just like I said at the beginning of one of the first workshops we hosted on installing the AICOS staff plug-in. I think everybody here has everything they already need to be successful. These tools are amplifiers of what you're already capable of doing. It also comes down to casting a vision for what AI can do and how it shows up to support you. I would encourage everyone to continue digging deeper and seeing how far you can stretch the capabilities of your AI Chief of Staff and the other teammates you're building skills and workflows around. And also how you're enabling your team to keep up with the speed at which you're building. We use the monthly workshops and boot camps as implementation sessions for new updates to the plugins and skills that I'll be creating and refining through my work outside of the monthly sessions. One insights, use case, skill or idea of what's even possible, that you may receive during a live session or skill share, can be worth it's weight in gold. This community is not just about learning, it's about implementing - and executing what you learn and have at your disposal as a resource with everything we've covered Claude and AI related this year.

Hey everyone, Sharing this before today's session because I had shared it with my mastermind but I thought it might be useful for the others to see what's possible after going through Darby's material once already. I want to be clear - I am not a developer but I am an operator that has been hiring, training, managing and putting teams that execute for many years. I went through the first class, sat with the folder structure Darby walked us through, his Chief of Staff and then added a few more pieces that I've learned and spent Saturday this weekend building this out. Wanted to show you where I landed so you can see what's on the other side of the work and sometimes seeing an example of a real work flow can help you see how you can put your own pieces together. Two things I want to set up before I get into the team, because they're the real lessons that I think are mission critical: Context and clarity are everything. This works because I gave each agent a clear role, a clear set of inputs, a clear definition of what good looks like, and clear hand-offs to other agents. Vague prompts produce vague work. Same as humans. If you can't write a clean "Job To Be Done" description for a person, you can't write one for an AI. I'm starting with my first team on low-risk work. On purpose. Same way I'd onboard a new human hire. Start them on work where the cost of getting it wrong is small. Watch how they perform. Build my own skill at managing them. Build trust. Then expand the scope. As I get better at managing the team and they get better at delivering, I add responsibility, just like a real team member. The mistake most founders make is handing AI a high-stakes task on day one and then deciding "AI doesn't work" when it underperforms. You wouldn't do that to a new hire. Here's what I built. A 7-agent AI team that reports to me each morning. I named them after Harry Potter characters because I'm bad with names and faces, and I started with ONE Mrs. Weasley as my Head of HR, and then she actually started naming the rest based on giving each one a personality that matched their role. It's been fun.

Hey y'all, here a quick start guide to using Obsidian as your forever brain and AI Chief of Staff's memory. (Get Obsidian) Obsidian → https://obsidian.md (Download Claude Desktop) Claude Desktop → https://claude.ai/download Let me know if you find this useful! Happy building, Darby

I dropped Catalyst v2.0.0 into the Gen AI University plugin library this week - it's in the Agentic CEO section of the Classroom. Twenty-nine new skills, designed to pair with the AI Chief of Staff without overlapping. On today's workshop, we didn't just install it. We built a new skill from scratch, live, in front of the cohort. A custom proposal generator that takes a discovery call transcript, scrapes the target organization's website in the background, detects the buyer type (chapter, conference, corporate, DMC, education), applies pricing guardrails, drafts the proposal, and renders a branded deck in Gamma using our MarketSauce theme. Discovery call transcript in. Proposal deck out. The skill didn't exist in Catalyst this morning. I built it from the existing skills to customize it live during the demo today. You do the exact same thing to customize these skills to your specific workflow. Simply describe the workflow you actually run. Claude drafts the skill file. You save it. You own it. If you're in the Agentic CEO program or GenAIU Premium membership, Catalyst v2.0.0 and this week's replay are int he Agentic CEO section of the Classroom. ==> Watch Replay & Get Resources Now Next workshop Tuesday. Darby