I Connected 9 Productivity Apps to One AI (Not the Way You Think)
The speaker demonstrates how to connect 9 productivity apps to Claude AI using MCPs (Model Context Protocol) to create a unified productivity system with full context awareness. The key innovation is the new My ICO MCP that provides Claude access to the speaker's entire productivity framework, enabling AI to understand and manage work across all connected tools.
Summary
The speaker discusses the evolution of AI integration in productivity tools, noting that early implementations like AI in Notion and ClickUp lacked sufficient context. Notebook LM improved this by allowing more context input, but the real breakthrough is MCPs—which connect external tools to Claude, providing comprehensive context across the entire productivity stack. The speaker connects multiple tools including ClickUp, Mirror, Heptabase, Readwise, Notebook LM, Gmail, Apple Notes, and Todoist to demonstrate how Claude can access information from all sources simultaneously.
A critical insight is that connecting these tools without proper structure creates problems for AI performance. The speaker emphasizes applying the ICO (Idea, Incubator, Organization) methodology across all tools so Claude can understand the underlying structure and efficiently find, compare, and organize information.
The speaker reveals a new My ICO MCP available to members, which allows Claude to access productivity system data including growth assignments, tool stack information, and course progress. This provides Claude with meta-level understanding of how the user's productivity system is structured and implemented. Rather than replacing specialized tools, MCPs enhance them by providing Claude with necessary context.
The speaker notes that this technology will likely cause some tools to become obsolete (citing how a new application replaced Day One and Mine Sera for their co-creator Paco), and predicts 2026 will be when individuals widely start building custom AI-powered solutions. However, the speaker emphasizes that success requires foundational understanding of tool-agnostic concepts and workflows, not just coding knowledge.
Key Insights
- Early AI implementations in tools like Notion and ClickUp felt disconnected because they lacked sufficient context about the user's broader productivity system and information landscape.
- MCPs are the real breakthrough for AI productivity because they allow Claude to connect to external tools and access full context across the entire user's tool stack, not just information within a single application.
- Connecting multiple productivity tools to Claude without proper structure and organization makes it difficult for AI to find the best information, so applying consistent methodologies like ICO across all tools is crucial for AI performance.
- The new My ICO MCP provides Claude with meta-level context about how well a user's productivity system is implemented by accessing growth assignments, tool stack information, and course progress across the entire My ICO platform.
- The speaker predicts that 2026 will be when AI-powered custom solutions become mainstream and individuals will build their own replacements for existing tools, but success requires foundational understanding of tool-agnostic workflows, not just coding knowledge.
Topics
Transcript
[0:00] What many people misunderstand is they always looked and I questioned this already since day one when AI got implemented into tools notion clickup he to run this locally inside the tools and ask questions and I always and I'm sure many of you out there too felt disconnected lack of context they wanted to get more context then we had notebook LM notebook became so powerful because now I was able to provide a lot more context throw it in share whatever comes [0:30] across no matter if it is YouTube videos or whatever and get a lot of information out of it. And now we have Gemini and Gemini allows us now to connect to Notebook LM…
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.