Claude writes better weekly reports than I did. Here is proof.
The speaker demonstrates how AI-powered weekly reports can automatically synthesize journal entries, notes, and captured content into personalized insights without manual review. Two different implementations are shown—one dashboard-style and one essay-style—proving the same underlying system can be customized to individual preferences and consumption habits.
Summary
The speaker begins by revisiting the concept of weekly reviews, explaining that while manual weekly reviews were historically powerful, AI has fundamentally changed how they can be generated. Rather than manually connecting dots from throughout the week, users can now generate comprehensive weekly reports with a single click by collecting and organizing information daily.
The speaker's personal weekly report, called "Week in Ink," is showcased as an 8-slide deck containing key metrics, insights, pivotal moments, embedded media, and personal highlights (like his daughter's swimming certification). The system automatically extracts content from a local folder containing journal entries dating back to 2017, which users populate throughout the week by sharing screenshots, meeting recordings, context notes, and other materials with AI agents.
A crucial feature is the automatic creation of a CRM tracking people, animals, and organizations mentioned in journal entries, plus an analytics dashboard showing which AI agents performed the most work during the week. The speaker also demonstrates a novel feature: an auto-generated podcast where two people discuss his week.
Paco Cantero, the co-founder of myICOR, presents an alternative implementation—a 47-page HTML weekly report formatted as philosophical essays rather than dashboards. His version emphasizes single-concept-per-slide design, pulling insights from chess games, piano practice, French learning sessions, and other life domains. The system automatically identifies and names new concepts (like "tacit knowing" and "fatigue amplification effect") by synthesizing his own journal language without external bias.
Both implementations demonstrate the same foundational system serving different consumption preferences. The speaker emphasizes that this approach is particularly valuable for people with ADHD, as the system automatically organizes captured information and extracts relevance based on user-defined key life elements (goals, projects, habits). The myICOR folder, available free to members, includes template SOPs, brand guidelines, and expansion packs with pre-built AI agents for consistent output quality.
Key Insights
- AI has fundamentally changed weekly reviews from a manual connecting-dots process into an automated one-click generation system, but only if users collect and organize information daily throughout the week rather than batching it at week's end
- The same underlying AI productivity system can generate radically different report formats—dashboards with multiple data points versus philosophical essays with single concepts—while maintaining the same foundation, proving customization to individual preference is what determines whether reviews actually stick
- AI agents automatically extract new concepts from a user's own journal language and naming them (like 'tacit knowing' and 'fatigue amplification effect') provides insights the user wouldn't generate themselves, creating a sense of growth without external bias
- Tracking which AI agents performed the most work during the week (measured by sessions) directly reveals which team members were critical to major launches or projects, providing transparency into resource allocation without manual logging
- For people with ADHD, the system works as a dream because it automatically organizes thrown-in content and extracts relevance, but this only functions if users have pre-defined their key life elements (goals, projects, habits, key interests) with clear guidelines
Topics
Transcript
[0:00] In my last video, you have seen that I said the Weekly Reviews Are Dead and I was referring to these manual reviews that people recommend where you go through the notes that you have taken throughout the week, connecting the dots, cleaning things up, and retrieving insights out of it. It was something very powerful in the past Doing these things manually versus not doing these things at all. And it all needs daily journaling and actually collecting information organizing it properly linking things together along the way to speed this weekly review up, [0:32] because if you do the connections while you're capturing information This will save you time later to get these insights you're looking for.…
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.