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.
Summary
The creator begins by reflecting on their earlier prediction that AI would eliminate traditional PKM (Personal Knowledge Management) tools like Heptabase, Tana, Notion, and Obsidian. They demonstrate three sophisticated applications built using Claude Sonnet 3.5 through Code Interpreter in a single session—all created from just one or two prompts without any custom skills, agents, or plugins.
The first application is a hybrid note-taking tool combining the best features of Tana (outlining), Obsidian (local folder access and Markdown formatting), and Heptabase (visualization). Built in under 30 minutes, it includes a browser-based interface with dark/light mode toggle, linked mentions, backlinks, sidebar navigation, database views with custom fields, grouping capabilities, board views, task management with Kanban boards, gallery views, journal functionality, and calendar integration. The creator emphasizes the responsiveness and polish of the UI despite being generated in a single prompt.
For the second application, the creator prompted Claude to analyze their entire Obsidian vault including custom-made plugins and theme, then build a new application representing the intention behind those plugins. The result is a Mac application with a menu bar item for quick notes, comprehensive task management, and the complete ICOR 4 Life folder structure (inner world, habits, goals, etc.). This app includes an interactive map interface, database structures for goals, habits, projects, topics, people, companies, notes, documents, and journaling. It features a planner with weekly views, drag-and-drop task scheduling, pinned items, paper note mode with light/dark themes, integrated AI functionality with Claude model selection, structured output capabilities, and even a terminal integration that can access the actual file system.
The creator emphasizes several remarkable aspects: the creation required no technical skills, only two straightforward prompts; the speed of development (under one hour for both apps); the use of a relatively inexpensive model (Sonnet 3.5); the polish and responsiveness of the interfaces; the integration of real data from actual Obsidian vaults; and the sophisticated database architecture that exceeds what Obsidian provides out-of-the-box. They reflect on the contrast with their earlier experience using Claude's previous version (Fable) to build tools over months with substantial token investment, now achieving far superior results in minutes.
Key Insights
- The creator built three fully-functional, polished applications using Claude Sonnet 3.5 in under one hour with essentially two prompts, compared to spending two months and substantial token budgets to build a similarly-featured web application with Opus 4 a year prior.
- Claude generated a Mac application that automatically understood and implemented the intention behind custom Obsidian plugins without explicit instruction by analyzing the actual plugin code in the vault's .obsidian folder.
- The AI-generated applications include sophisticated database structures with multiple view types (board, gallery, calendar, table), grouping capabilities, and relationships that exceed Obsidian's native capabilities despite being created in a single prompt.
- The creator used a slash goal parameter in Claude to enable continuous self-checking and goal verification, allowing the AI to iterate internally until achieving the specified objective without manual intervention.
- The generated applications successfully integrated real data by actually reading the user's file system and Obsidian vault structure, creating functional tools that work with existing personal data immediately upon generation.
Topics
Transcript
[0:00] do you remember earlier this year when I said AI will kill all the PKM tools! That we've been using in the past years. Like Heptabase, Tana, Notion, and so on? And for me, it did back then already. I used a local folder and I built my own tools, and yet it was very vibe code-y and a lot of effort went into it. But today, it is not only so easy and fast to create, but also cheap. Look at this. I built three applications using Sonnet 5.5 with high effort in Claude Code. [0:30] It's just one prompt, and we will go into this in detail . And what it created in no time, that's the…
Full transcript available for MurmurCast members
Sign Up to AccessMore from ICOR with Tom | AI Productivity
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.
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.