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.
Summary
The speaker describes a fundamental shift in how note-taking and personal knowledge management works. Traditionally, people capture notes throughout the week (in notebooks, apps, or sticky notes) and then conduct a time-consuming weekly review to organize, connect, and file them. The speaker admits he never consistently did this review because it felt exhausting. As an alternative, many adopted tools like Obsidian, Tana, or Heptabase that encourage manual linking of notes as you create them—connecting related ideas node-by-node. While better than disconnected notes, this manual linking still created friction.
The breakthrough came when the speaker realized that AI no longer needs humans to perform this manual work. However, the critical insight is that AI doesn't work by magic—it requires structure. The speaker created what he calls a 'scaffold': a local folder organized around core life concepts including key elements, topics, projects, goals, and habits. Each category has definitions that explain what matters. When a new note is captured (via voice dictation), Claude AI reads it against this scaffold structure and automatically files it in the correct location, extracts meaningful information, and creates connections.
With this system, the speaker now captures notes throughout the day without filing, tagging, or deciding where they belong. He simply dictates to his phone, and the system handles organization. The remarkable feature is that months or even years later, when a related note is captured, the system surfaces the original connection—creating what the speaker calls 'serendipity on autopilot.' He provides a concrete example: a thought from 2022 about the dream he and co-founder Paco had was automatically connected to something they shipped that week.
Most significantly, the weekly review has been replaced entirely. Instead of manually reviewing his week, he receives an automated 'Friday recap' that the system generates. This recap doesn't just list what he captured—it draws connections across different life areas that he wouldn't have noticed himself. The speaker emphasizes that this isn't a faster version of the old process; it's a fundamentally different output that no human could produce by manually reviewing notes.
The speaker concludes that this shift represents a larger transition away from proprietary note-taking tools. Apps like Evernote, Notion, Tana, and Heptabase were valuable primarily because they provided databases—proprietary systems that you depended on. Now, with AI's ability to create and manage databases, these tools have become optional utilities rather than essential applications. Users can maintain their own data in a simple folder structure with a clean interface (which the speaker calls a 'cockpit') layered on top.
Key Insights
- The speaker argues that traditional weekly reviews fail because people are too exhausted at week's end to review notes, making manual linking and collection ultimately unworkable for most people
- Manual note-linking, which the speaker perfected in tools like Tana and Heptabase, was always the hidden friction in the system—only once AI arrived at sufficient capability did this friction become visible and replaceable
- The critical component enabling AI to organize notes effectively is not the AI itself but the 'scaffold'—a folder structure with explicit definitions of what constitutes key elements, topics, projects, and habits in the user's life
- The speaker claims that legacy note-taking tools like Notion, Tana, and Heptabase have been rendered obsolete because their primary value was the proprietary database they controlled—now users can create their own database with AI and no longer depend on the tool vendor
- The automated Friday recap connects insights across different life areas and surfaces patterns the user wouldn't discover through manual review, such as linking a 4-year-old captured thought directly to a current project launch
Topics
Transcript
[0:00] If you follow me on this channel, you know that my whole life and business runs through one local folder and cloth and that's it. But there's one member in our inner circle who stopped me this week during our coaching session. He's a journaler, a real journaler for years. Pen, paper, a notebook he actually carries. And every single week, he did the same ritual. He collected his notes, all of them. And on the weekend, he sat down and reviewed them page by page to make sense of what happened. Then he moved his notes into the system I'm [0:30] about to show you. And that whole weekly ritual, the thing he'd done for years, just became…
Full transcript available for MurmurCast members
Sign Up to AccessMore from ICOR with Tom | AI Productivity
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.
Our AI invented the numbers. We caught it.
The hosts discuss the importance of double-checking AI outputs and validating information, emphasizing that this is not a new problem but rather a longstanding practice required with any information source. They explore how AI tools can be customized to individual workflows and contexts, arguing that understanding foundational methodology matters more than specific tools.
An AI Just Handed Me a Fake $67B Statistic
The speaker shares how an AI confidently generated a completely fabricated $67.4 billion statistic while researching AI hallucinations, then explains his systematic approach to combating AI misinformation: using dual independent search engines to cross-check answers and identify where hallucinations occur.
AI Is Quietly Taking Your Memory
AI companies are racing to own users' context and memory through integrated tools like Claude in Slack and ChatGPT's auto-memory features, creating a lock-in trap. The speaker argues users should own their context (expensive, irreplaceable) in local plain text files while renting the AI model (cheap, replaceable), and demonstrates his personal knowledge assistant system built on markdown files that work with any AI model.
My AI Team Now Has an Interface. All 12 Agents. Free.
Tom, creator of the iCola methodology, releases My PKA version 3 with a free interface (My PKA Cockpit) that provides 12 pre-built AI agents for productivity, note-taking, health tracking, document management, and task planning—all running locally in a folder structure accessible via Claude and a web interface.