Your knowledge should outlive every AI tool you use.
The speaker clarifies the distinction between the ICOR methodology (a tool-agnostic productivity framework) and its implementations like the ICOR for Life scaffold and myPKA AI team, emphasizing that users can adopt the core principles in any tool they prefer. They announce plans to restructure their membership platform by separating these components to reduce confusion and help users understand they're not locked into specific tools or systems.
Summary
The video addresses confusion around the ICOR for Life folder and myPKA AI team concept by explaining their relationship and purpose. ICOR stands for a Personal Knowledge Assistance system with an orchestrator agent named Larry who delegates tasks to specialized AI agents (Silas, Iris, Charta, Pixel, Vera, Mack, and Vex), each handling different functions like text organization, markdown documentation, infographic creation, and quality verification.
The core issue discussed is that distributing ICOR for Life as an all-in-one solution alongside Obsidian integration created the false impression that users must adopt this specific methodology, the included AI team, and Obsidian to make the system work. In reality, the ICOR methodology is completely tool-agnostic and has always been independent of any particular software.
The speaker explains that the ICOR framework helps users map their entire productivity system—distinguishing between core applications (which contain critical information) and utility apps (which support work without storing core knowledge). They illustrate this with their own tool transitions: they previously used Heptabase as a core app, then shifted to a local folder approach, while co-founder Paco uses Tana and has built his own Mindset application.
A critical revelation is that the myPKA AI team should be classified as a utility app, not a core application. This means users can replace it with Claude, ChatGPT, or any other AI system without losing their knowledge structure. Similarly, the ICOR for Life implementation can happen in Notion, Heptabase, Tana, or any knowledge management tool—the methodology remains constant while tools vary.
The speaker announces a restructuring plan to split the ICOR for Life scaffold and myPKA scaffold into separate downloadable components, along with an expansion of the membership platform's expansion packs area to offer multiple interface options and configurations. They emphasize that member implementations demonstrate diverse real-world approaches to ICOR, with examples like Steven and Mike showing how different professionals adapt the system to their tool stacks.
Key Insights
- The speaker argues that the ICOR methodology's core concepts and workflows are immutable and set in stone, but the tools used to implement them can be freely swapped without compromising the system's integrity
- The speaker claims that myPKA should be classified as a utility app rather than a core application, meaning users can replace the AI team with Claude, ChatGPT, or other systems while maintaining their knowledge structure
- The speaker states that using a local folder approach instead of tools like Heptabase provided greater control and better AI integration because it allowed direct node manipulation and brought more context into the system
- The speaker contends that understanding the ICOR framework creates resilience against tool-switching temptation because users can clearly see why they chose their current tool and evaluate whether switching is truly beneficial
- The speaker argues that merging the myPKA AI team with the ICOR for Life scaffold into one folder was beneficial for advanced users like Paco who can code, but is unnecessary complexity for most professionals
Topics
Transcript
[0:00] that's an Important Video in my opinion, to share with everybody who is interested in using AI combined with your knowledge management and your action system. And those following us know that we share the ICOR for Life scaffold. It is a folder that we've been using for months, as you can see here. It contains of several folders that organize your knowledge and also your action inside one folder, and it also has an AI team in there with several agents doing different things, And here's a quick video of our latest [0:30] AI team introducing themselves what they are capable of and what they're here for. Let's have a look One folder, a whole team of AI…
Full transcript available for MurmurCast members
Sign Up to AccessMore from ICOR with Tom | AI Productivity
Claude alone took 3 minutes. With Jev, 21 seconds.
A demonstration comparing AI slide deck creation using Claude alone versus Claude integrated with Jev, showing that the hybrid approach completed the task in 21 seconds for $8 with proper formatting, while Claude-only took 3+ minutes and cost $49 with poor formatting.
Why I stick to Claude for work (most of the time)
The creator demonstrates why Claude is their preferred AI for work by comparing it with ChatGPT across multiple tests, showing that Claude better adheres to custom instructions and agentic workflows defined in local folder structures. The key advantage lies in using organized, LLM-agnostic folder systems with agents.md files rather than relying on auto-memory features.
You are using the wrong Claude for work! (Here is proof)
A video demonstrating that Claude Code is significantly more powerful than Claude Cowork for professional knowledge workers, showing how Claude Code better understands folder context, enforces safety rules, orchestrates sub-agents with different models, and creates persistent file outputs rather than temporary artifacts.
Obsidian is the tool I teach in. Keep the one you have.
The creator addresses criticism about switching to Obsidian after previously promoting other tools, clarifying that his tool-agnostic ICOR methodology remains unchanged and that Obsidian is simply an interface layer for his folder-based system. He emphasizes that the underlying folder structure, AI automation, and productivity principles are identical regardless of which tool visualizes the content.
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.