AI is just hype, they said...
The creator showcases a fully custom-built learning and membership platform called MyICO, constructed entirely by an AI team using Claude and a local folder-based agent orchestration system. The platform features self-hosted video, semantic search, community management, coaching session libraries with timestamped chapters, and a tool-finder database. Three new courses are announced teaching users how to replicate this AI team structure for their own productivity or knowledge management needs.
Summary
The video is a tour of the newly launched MyICO platform, a self-built membership and learning application created entirely by an AI team orchestrated through Claude. The creator explains that after years of bouncing between platforms like Circle, Mighty Networks, and WordPress, he and co-founder Paco decided to build their own platform from scratch using an AI agent team structured around a local folder system.
The platform's community is entity-based, meaning comments and discussions are contextually linked to specific tools, lessons, or coaching sessions rather than existing in isolated threads. The platform uses a self-hosted video system giving full control over transcripts and timestamps, enabling a powerful search experience where users can find a keyword like 'Claude,' get a glossary definition, jump to a relevant lesson, and even land at an exact timestamp in a recorded coaching session.
A key feature is 'Jax,' an AI community manager trained on thousands of articles, videos, podcast episodes, lessons, and coaching recordings. Jax can answer member questions, escalate to human founders when needed, and continuously learns from the answers Paco and the creator provide. The support ticket system has also been replaced with a self-made AI-powered version.
Three new workshop courses are introduced: a Foundations course (building the base folder and agent structure), an IPA (Intelligent Process Automation) system course, and a PKM (Personal Knowledge Assistance) system course. The foundation is an orchestrator agent named Larry, supported by Nolan (HR agent), Pex (deep research analyst), Iris (design system agent), and Pixel (thumbnail creator), among others. The creator demonstrates downloading the PKM course folder and immediately activating Larry inside Claude Code or Obsidian's terminal plugin.
The ICO methodology underpins everything taught — covering productivity end-to-end from note-taking and personal knowledge management to task management, automation, and AI. The platform also includes a tool-finder showing real community usage data across 420+ tools filtered by role and industry, a workstream creator for visualizing automated vs. manual workflows, and an ICO framework canvas for mapping personal tool stacks. The creator emphasizes that the entire platform, including design, was produced by the AI team, citing the jump in capability with Claude Opus 4.7 as a significant turning point.
Key Insights
- The creator argues that the entire MyICO platform — including its design system, database architecture, and application security — was built by an AI agent team orchestrated through Claude using only a local folder structure, with no traditional development team.
- The platform's search is semantic and deeply integrated with self-hosted video, allowing a search result to open a coaching recording and jump directly to the exact timestamp where a topic is discussed — something the creator says he had been working toward for years.
- The creator claims that with Claude Opus 4.7, the design agent Iris became capable enough to replace dedicated design platforms like Claude Artifacts/Design, handling the full design system for the application.
- Jax, the AI community manager, is described as continuously learning from the real answers Paco and the creator give to community members, and is trained on thousands of articles, videos, podcast episodes, lessons, and the full ICO journey book — enabling it to point users to specific coaching session timestamps.
- The creator states that MyICO is run by just two people — himself and Paco — with the AI team replacing what would otherwise require additional staff, including the entire support ticket system, content management, and community moderation.
Topics
Transcript
[0:00] Everybody, it's done. It has been a bit quiet on this channel, but there was a reason and it was a big one. It was the launch of our newest version of my eye core. And everything that I will show you in this video was built by my AI team that I showed you already on this channel. How I built this from scratch is just based on a local folder and using claude. And I want to take you on a tour through this application because this is not something simple. It's something very complex and if anybody [0:30] says AI is just hype, watch this because impossible to do something like this just a year ago.…
Full transcript available for MurmurCast members
Sign Up to AccessMore from ICOR with Tom | AI Productivity
I do not download invoices anymore. My folder and Claude do it.
The speaker demonstrates how he uses AI (Claude) integrated with his local folder system to automate invoice collection for his accountant, downloading 36 invoices in 5 minutes with minimal manual intervention. He explains his AI team methodology, work streams, and how persistent local knowledge bases enable AI to handle recurring tasks independently without constant re-explanation.
Claude finished the work. Then I lost it in the chat.
A creator demonstrates a comprehensive local-folder-based system for managing AI-generated deliverables asynchronously, featuring an interactive browser interface that tracks decisions, changes, and conversations without relying on external databases or web applications. The system enables collaborative editing, visual annotations, and automatic context preservation across multiple parallel AI projects.
Claude writes better weekly reports than I did. Here is proof.
The speaker demonstrates how AI-powered weekly reports can automatically synthesize journal entries, notes, and captured content into personalized insights without manual review. Two different implementations are shown—one dashboard-style and one essay-style—proving the same underlying system can be customized to individual preferences and consumption habits.
I stopped doing my weekly review. The AI does it now.
The speaker has replaced traditional weekly reviews and manual note-linking with an AI-powered system built on a local folder structure called a 'scaffold.' This approach eliminates the time-consuming review ritual while enabling the AI to automatically connect notes and surface meaningful patterns that humans would miss.
I Made Opus and Fable Grade Each Other. Opus Admitted It Lost.
The creator demonstrates real-world AI applications in their productivity business using Claude Fable and Opus, showing how Fable excels at comprehensive analysis of complex systems while comparing its performance to Opus on specific tasks. The key finding is that Fable's holistic understanding justifies its higher cost for business-critical audits and optimizations.