New Shiny App Syndrome Ends with This Map
The video introduces the ICO framework, a Venn diagram-based map for visualizing your productivity tool stack across four quadrants: personal/business and information/action. The presenter demonstrates how to categorize tools as core applications, satellite apps, or utility apps, and how to identify redundancies and gaps in your system. The goal is to build tool-agnostic clarity about your productivity system rather than chasing new apps.
Summary
The video addresses 'shiny object syndrome' — the tendency to constantly seek new productivity tools — by arguing that the root problem is typically a lack of understanding of one's overall productivity system, not a lack of tools. The presenter introduces the ICO framework, a Venn diagram composed of four overlapping areas: Personal Knowledge Management (PKM), Personal Project Management (PPM), Business Project Management (BPM), and Business Knowledge Management (BKM). The left side of the diagram represents personal use, the right side represents business use, the top relates to information, and the bottom relates to action. 'Business' is defined broadly to include anything shared with a team, clients, or used to organize a business — even for solopreneurs.
The presenter walks through a digital implementation of this map, showing how tools like ClickUp, Gmail, Google Calendar, Todoist, and a PKM vault can be dragged and dropped into the appropriate quadrants. Placing a tool in the center of all four circles means it is used across every area of the system. Tools placed inside the circles are classified as 'core applications,' which are difficult to remove because they store critical, hard-to-migrate data. Examples include Gmail, which could contain decades of information.
The framework also introduces two additional tool classifications beyond core apps. 'Satellite apps' are tools that depend on a core application to function — like Superhuman, which requires Gmail access — and are easier to replace since data lives in the core. 'Utility apps' are standalone tools that improve workflows without storing essential data or directly integrating with core tools; examples include Raycast and Claude. Tools like Sansama are shown as potentially being either satellite or core apps depending on whether data is stored within them.
Each tool on the map can be clicked to access a detail page where users can specify their integration level (testing, needs alternative, or deeply integrated), cost, devices used, and secondary use-case categories aligned with the ICOR methodology (e.g., idea incubator, team communication, goal setting, project management). This granular categorization helps users identify gaps — for instance, if a PKM tool doesn't cover quick capture, a tool like Tana can be added specifically for that purpose. The presenter emphasizes that this map serves as a single source of truth for understanding one's tool stack and can even inform AI assistants via an MCP connector about how tools are being used.
Key Insights
- The presenter argues that shiny object syndrome stems not from a lack of tools but from a lack of understanding of one's tool-agnostic productivity system, making tool-switching often counterproductive.
- The presenter defines 'core applications' as tools placed inside the ICO circles that are very hard to remove because switching away from them risks losing significant stored data — citing Gmail as an example where decades of information could be lost by migrating to Outlook.
- The presenter distinguishes satellite apps from core apps by explaining that satellite apps — like Superhuman relative to Gmail — cannot function independently and wrap around a core, making them easy to swap out without data loss.
- The presenter classifies tools like Sansama as potentially satellite or core depending on whether data is actually stored in them, noting that if Sansama only represents data from other sources, removing it leaves all underlying data in the core apps intact.
- The presenter explains that the tool detail pages — where secondary categories like 'idea incubator,' 'team communication,' and 'quick capture' are filled in — allow users to spot gaps in their system and deliberately add tools to cover missing functions, such as adding Tana specifically for quick capture.
Topics
Transcript
[0:00] If you're prone for the shiny object syndrome that you're always looking out for the next productivity tool that might help you to overcome any friction and anxiety, this video is for you because it's usually not the lack of tools in your life but the lack of an understanding of your productivity system which is tool agnostic. And in this video, we will merge both together, getting the clarity about our tool stack that we use every day and how it fits into your tool agnostic concepts and workflows in your life. Let's dive into [0:30] this. Here's one of the most important things to understand your productivity system to end because eventually this map here will represent…
Full transcript available for MurmurCast members
Sign Up to AccessMore from ICOR with Tom | AI Productivity
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.
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.