I ingested all my YouTube videos into an LLM wiki and turned them into a connected second brain that my AI OS can actually reason over. In this one I show you how to build the same thing in about five minutes using Claude Code and Obsidian, based on Andrej Karpathy's LLM knowledge base idea. You drop in sources, the AI reads them, splits them into cross-linked wiki pages, and keeps the whole thing organized with routing rules so it can find anything fast. By the end you'll know how to set up the vault, write the schema, ingest a PDF and a URL, and decide when to keep your wiki flat versus structured.

From $40K AI projects and first clients to custom CRMs, AI operating systems, and production-ready automations, another week inside AIS+ proved that consistent building keeps creating opportunities. 🚀 Standout Wins of the Week inside AIS+ 👉 @Kobe Shemesh closed a $40K upfront AI project after refining his Claude Code workflow, proving that small improvements in execution can create massive business results. 👉 @Galyn Fergerson landed her first client just 6 days into AIS+, turning a discovery call into a $750 AI OS project before even finishing the automation course. 👉 @Girish Mohan built an AI Scrum Master that now prioritizes his calendar, tasks, and deals automatically—helping him execute every day with more focus. 👉 William Rendall was promoted to AI Workstream Strategy Lead less than three months after joining AIS+, crediting the community for accelerating his growth. 👉 Diane McCracken celebrated her 100th Claude Code session at 68 years old, showing that curiosity and consistency matter far more than experience. ⸻ 🎥 Super Win Spotlight | @Ahmad Abd Alkarim Ahmad joined AIS+ with years of leadership experience but wanted a better way to turn ideas into action. Today, his custom AI Operating System helps him manage projects, analyze business problems, and support his team without slowing anyone down. His biggest lesson? Don't just watch. Build. Practice. Share what you learn. That's where the real return comes from. 🎥 Watch Ahmad's story 👇 ✨ Every week, members are turning ideas into systems, skills into businesses, and momentum into real opportunities. Step inside AI Automation Society Plus and start building assets, systems, and skills that compound 🚀

Diving Deep into the WAT Framework, Token Optimization, and CLAUDE.md Just wrapped up Day 1! Instead of just mindlessly running the setup, I had a great discussion with Claude about the core architecture and the role of CLAUDE.md. It gave me some really solid "aha!" moments about how AI agents actually scale, so I wanted to share my takeaways with the community. 📝 What I Built - The Deliverable: A fully automated newsletter system that takes a single prompt, conducts research via Perplexity, generates visuals with Nano Banana, formats everything in HTML, and sends a polished email via Gmail. - The Setup: Configured the project structure based on the WAT framework (Workflows + Agent + Tools) driven by CLAUDE.md. 💡 My "Aha!" Moments & Core Takeaways 1. What does CLAUDE.md actually do? I realized that CLAUDE.md is the literal "brain transplant" (system prompt) that turns a generic, jack-of-all-trades AI into a highly structured, autonomous operations manager for this specific project. It strictly enforces: - Role Limitation: Stopping Claude from doing everything probabilistically and forcing it to delegate to deterministic Python scripts (tools). - Shared Context: Drilling in the exact folder architecture (workflows/, tools/) and setting ground rules, like keeping deliverables in cloud services. - The Self-Improvement Loop: Commanding the agent to not just report errors, but to actively fix the scripts and update the markdown documentation on the fly. 2. The Dilemma of Centralized Management vs. Token Bloat While I loved the idea of keeping all workflows and tools in one project folder for reusability, a critical question hit me: "As we add dozens of workflows, won't Claude read everything every time and absolutely explode our token consumption?" 【How it's solved】 I learned that robust systems don't force the AI to read every single markdown file from the jump. Instead, they use a lightweight index file or vector search (RAG) to let the system pull only the specific workflow required for the task. It was eye-opening to see how decoupling AI reasoning from deterministic system control keeps the context window clean and scalable.

Let's get to know each other! Comment below sharing where you are in the world, a career goal you have, and something you like to do for fun. 😊

Day 1 Build: AI Express 📬 What I built: A newsletter that makes itself. I type a topic — it researches the news, designs graphics with real stats, and emails a polished issue to my list. I just review and hit approve. First issue arrived in my inbox today! (screenshot attached) One thing learned and clicked: Using the Perplexity API is vastly more cost-effective for web research than standard, pay-as-you-go Claude API models. A deep topic research query that costs approximately $0.20 to execute with Perplexity can quickly run upwards of $3 in tokens with Claude One thing I'd improve: Give more context information at the planning phase