Stop Taking Notes Like This. Your System Is Broken.
The speaker describes evolving from paper notebooks to a hybrid digital note-taking system that separates shallow thinking (quick capture in databases) from deep thinking (visual synthesis on whiteboards). Rather than building a "second brain" through external storage, the approach integrates digital tools as an extension of natural brain function using strategic note-taking focused on decisions, actions, and key insights.
Summary
The speaker shares a decade-long journey optimizing note-taking systems across multiple parallel projects. Initial attempts using single notebooks proved inefficient for searchability, leading to the development of a "single source of truth" concept—knowing exactly where to find specific information. The evolution progressed through paper notebooks organized by project, handwriting apps on iPad (gaining searchable text), and eventually typed notes in PKM tools like Hepbase. However, walls of text created comprehension problems, prompting adoption of visual notes including diagrams, flowcharts, and mind maps.
The core methodology distinguishes between shallow and deep thinking. Shallow thinking uses rapid note capture (meetings, temporary information) in database tools like Hepbase, which support tagging and connection to relevant content (e.g., person databases). Deep thinking occurs in visual tools like Hector or Miro, where complex information is laid out on whiteboards for synthesis and problem-solving.
A critical concept challenges the popular "second brain" approach. Rather than outsourcing brain storage by collecting unlimited information, the speaker advocates for an "optimized one brain with two parts"—physical and digital—where the digital component integrates as a functional extension rather than external storage. This requires building systems around how brains naturally work, eliminating the need for conscious decision-making about information placement.
The speaker introduced "strategic note-taking" as the optimal balance after discovering that attempting to transcribe everything prevented meeting engagement and created post-meeting chaos. Strategic note-taking focuses exclusively on capturing decisions, actions needed, and key insights. The shallow/deep split reduces friction by allowing temporary notes to be calmly transferred to deep thinking systems later, improving both note-taking speed and organization accuracy.
Key Insights
- The speaker evolved from paper notebooks to digital PKM tools because typing is faster than handwriting, but discovered that walls of text eliminate recognizable patterns needed for quick information identification later.
- The speaker differentiates between a 'second brain' approach (which simply creates another searchable repository with potentially outdated information) and an 'optimized one brain with two parts' (physical and digital) that functions as an integrated system based on how brains naturally work.
- The speaker previously stopped taking notes entirely because the capture process was too slow to follow meetings with full attention while also knowing that information would need to be looked up later anyway.
- Strategic note-taking focuses specifically on capturing decisions, actions needed, and key insights rather than attempting to transcribe everything, which both speeds up note-taking and maintains meeting engagement.
- The shallow thinking system uses notes to balance cognitive load by capturing key points during meetings, while relevant information can be calmly moved to the deep thinking system later when returning to the desktop, reducing decision fatigue about placement.
Topics
Transcript
[0:00] I've been working on several projects in parallel for more than a decade now. It was messy to say the least in the beginning. Having just one notebook didn't do the trick as having information about completely independent projects inside one book make searchability impossible. Thanks to my handwriting and scribbles, I was able to have a slight idea where to find information I'd collected earlier. To improve things, I came up with the idea of the single source of truth. In simple terms, I wanted to know exactly the place, the single source I needed to [0:31] look up to find the correct information I need. Hence, I started to carry around several paper notebooks trying to split…
Full transcript available for MurmurCast members
Sign Up to AccessMore from ICOR with Tom | AI Productivity
Claude sucks. And here is why.
This video explores why Claude and other AI models produce inconsistent results, examining how model selection (Haiku vs Sonnet vs Opus vs Claude 3.5 Fable), effort levels, prompt clarity, and system context dramatically affect output quality. The speaker demonstrates these differences through a Venn diagram creation task and advocates for using organized folder systems with documented SOPs and code-based solutions to ensure consistent AI performance.
Claude can now prompt its own SESSIONS. I built the boss.
Claude now has the ability to interact with multiple sessions, allowing a streamlined orchestration of tasks through an agent called Larry. This integration can simplify task management and enhance productivity by enabling a single main session to oversee various sub-sessions or tasks.
I switched off Claude's memory. My folder does it better.
Tom explains why he disabled Claude's native memory feature and instead built a local folder-based system (myPKM) to maintain persistent context with AI agents. He shares an audit revealing systemic issues like contradictory documentation, forgotten rules, and parallel session conflicts, then outlines how to systematically fix these problems using the ICOR productivity methodology.
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.