I Can Build a $11 Billion Productivity App with AI (You Can Too)
The speaker demonstrates how modern AI models (Claude Sonnet 3.5) enable anyone to build sophisticated productivity applications without extensive coding knowledge, using the newly rebuilt myICOR membership platform as proof. He argues that pre-built platforms like Notion, Circle, and Mighty Networks are becoming obsolete as AI democratizes custom application development, and announces a live workshop teaching the conceptual and technical skills needed to build such apps.
Summary
The speaker shares his three-day journey rebuilding the myICOR membership platform from scratch using Claude Sonnet 3.5, demonstrating that custom application development is now accessible to professionals without deep technical backgrounds. He traces his evolution from paying €10,000 for a WordPress-based membership platform (which failed to deliver value) through multiple platform migrations (Circle, Mighty Networks) to finally building his own solution with AI assistance.
The core argument centers on a shift in capability: six months ago, the speaker would have discouraged others from building custom apps, believing the complexity was prohibitive. However, community feedback and the capabilities of current AI models convinced him that the barrier to entry has fundamentally lowered. He emphasizes that success requires not coding skills but "tool-agnostic knowledge"—understanding process mapping, system design, and the ICOR methodology (a framework for personal and business productivity systems he developed).
The speaker details his platform's architecture, including database structure using Supabase as a replacement for Airtable, and demonstrates the new myICOR interface's improvements over the previous version. Notably, he built a native iOS application in just half a day using AI, a feature that would have cost €17,000-€35,000 annually through traditional platforms like Mighty Networks. The platform includes complex features: membership tiers, payment handling, commenting systems, course management, social functionality, and mobile optimization.
He credits the ICOR framework—which maps what information users capture daily, where they store it, and how systems interconnect—as the foundational thinking that enables AI to build effective custom tools. The speaker positions this as the future: highly customized digital environments replacing one-size-fits-all platforms that users continuously struggle to adapt to their actual workflows.
Key Insights
- The speaker's assessment of custom app viability changed fundamentally within six months due to AI model improvements and community readiness, shifting from believing it was a waste of time to asserting that pre-built platforms like Notion, Heptabase, and Tana will be obsolete in coming years
- Building the complete myICOR membership platform required only three days of work, with a native iOS application version completed in half a day—contrasting dramatically with years of previous iterations and the €17,000-€35,000 annual fees charged by competitors like Mighty Networks for similar functionality
- The speaker spent €10,000 on a WordPress-based membership platform in 2019 that delivered no value beyond an empty template, leading him to conclude that pre-built solutions fail because they cannot serve diverse use cases without bloating with unnecessary features
- The ICOR methodology provides the foundational framework for building effective custom tools by mapping information capture, storage, and retrieval patterns—described as 'tool-agnostic knowledge' that enables AI to generate practical applications rather than generic ones
- The speaker considers the code quality generated by current AI models equivalent to or better than much production code from human developers, noting that poor code quality is a human problem independent of whether it originates from AI or developers
Topics
Transcript
[0:00] Three days ago, I showed you already proof of concept that with Sonnet 5.5 you can quickly create productivity tools to your liking. And if you would have asked me that anybody can now create their apps to their liking six months ago, I would have said, " I think you waste your time because there goes so much into it to know." And I'm not talking about coding, I'm talking about understanding how a tool is set up, how a system works, and all these things , and yet we had so many members who are all busy professionals inside our community who [0:31] started vibe coding their apps. And then I published a set of plugins that…
Full transcript available for MurmurCast members
Sign Up to AccessMore from ICOR with Tom | AI Productivity
I gave Claude 4 years of our work. It built this app.
A developer used Claude Sonnet 5.5 to build a fully functional ICOR-based productivity application in just one hour by providing the AI with four years of accumulated productivity knowledge and content. The resulting app successfully implements complex ICOR methodology concepts including inbox management, task prioritization, interruption handling, and life dimension tracking, though it needs UI/design refinement.
Claude just replaced every productivity app I use.
A content creator demonstrates how Claude's Sonnet 3.5 model with Code Interpreter can replace multiple productivity apps by building three fully-functional applications in under an hour with minimal prompting. The creator showcases a note-taking app with database features, a Mac application integrating their custom Obsidian plugins and ICOR life management methodology, and highlights the unprecedented speed and polish achievable without traditional development skills.
My AI team took 8 hours. Claude Sonnet 5.5 took 15 minutes.
A creator comparing an 8-hour AI team project with a 15-minute Claude Sonnet 5.5 solution reveals that excessive guardrails and restrictions paradoxically hindered the multi-agent system's performance. The speaker demonstrates how reducing constraints and context allows AI to produce more creative and functional results, though both approaches have significant limitations for production use.
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.
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.