How I Find Any Meeting Note in Seconds (No Complex System Required)
The speaker demonstrates how to use backlinking and journal-based note-taking in PKM tools like Heptabase to quickly capture and retrieve meeting information. By mentioning people, projects, and topics during meetings, you create interconnected context that enables rapid information retrieval through backlinks and search.
Summary
The speaker introduces a method for dramatically improving productivity in Personal Knowledge Management (PKM), one of four areas in a comprehensive productivity system. He explains that his breakthrough came when Rome Research introduced backlinking, allowing him to quickly access previously discussed information during fast-paced, context-switching work environments.
The core technique involves using a daily journal feature in tools like Heptabase to take meeting notes. Instead of complex organizational systems, the speaker simply mentions people, projects, and topics by using the @ symbol to create or link to cards on the fly. For example, during a meeting about Project Phoenix and Project Elephant with someone named Gandalf, he creates these references naturally while note-taking.
The speaker emphasizes that the real power emerges through backlinking—when you later search for a person or project, all instances where they were mentioned appear automatically, showing contextual connections. For actions that emerge during meetings, he uses checkbox syntax in Heptabase but warns against managing all tasks in the PKM system. Instead, actions should be processed from the inbox and moved to dedicated task management tools.
He stresses that this method works across multiple tools (Obsidian, Reflect, etc.) and requires minimal overhead—just consistent daily journaling with mentions. By establishing one trusted location for information, your mind knows where to look, and you can retrieve context from calendar dates or simple searches. The speaker concludes that this foundation is where busy professionals should start before attempting more complex PKM optimization.
Key Insights
- Rome Research's introduction of backlinking was a pivotal moment that enabled the speaker to become more responsive by having previously discussed information immediately at hand during meetings and context switching
- The speaker argues that many people incorrectly try to manage all tasks within their PKM system, when in fact dedicated task managers and project management tools should handle this complexity for busy professionals with hundreds of tasks
- Simply taking daily journal notes with mentions of people and projects automatically creates context that can be retrieved later through backlinks, without requiring upfront organizational effort
- The power of backlinking is demonstrated through the ability to search for a person and see all meetings and contexts they were mentioned in, revealing connections between different projects and people
- The speaker believes that most members joining PKM communities are overwhelmed and should start with journaling as the foundation rather than attempting to use one tool for everything
Topics
Transcript
[0:00] What I'm about to show you will 10x your productivity in a very specific area of your productivity system. In Icor, we talk about four areas of a productivity system. The PKM, personal knowledge management, the PPM, personal project management or task management. BPM, business project management, and BKM, business knowledge management. These four areas define a productivity system end to end for any professional out there. Today we talk only about PKM and how you can 10x your productivity there. So you see these are the tools that I [0:30] have in my PKM and essentially it's hepta basease and reader that is really relevant but does it matter for you out there if you're using something else?…
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.