Heptabase PDF Review: Obsidian and Scrintal Don't Win
The speaker demonstrates Heptabase's powerful PDF annotation and research workflow, showing how highlights can be extracted, connected across whiteboards, and integrated with other notes to create a comprehensive personal knowledge management system that rivals tools like Obsidian and Scrintal.
Summary
The speaker, an experienced PKM system tester with over a decade of experience, showcases Heptabase as their preferred knowledge management tool. They highlight how Heptabase combines the best features of competing tools including Scrintal, Obsidian, Tana, and MarginNote's PDF annotation capabilities. The core demonstration focuses on a sophisticated PDF research workflow using a PhD thesis as an example. Users can upload PDFs as cards, highlight text or areas (particularly useful for images), and add notes to these highlights. The key innovation is the drag-and-drop functionality that allows users to extract highlights directly onto whiteboards, visually representing connections between different pieces of information. The system tracks where highlights appear across multiple whiteboards through an info panel, enabling users to navigate between contexts. When reading through PDFs, users can locate highlights in their original source with a single click, which automatically opens the PDF and scrolls to the relevant section. All connections are bidirectional—emails, notes, and other content can be linked to highlights, creating an interconnected web of information. The speaker emphasizes that this isn't an isolated feature but deeply integrates with daily journaling, allowing users to review past notes and see how they connect to research highlights. The speaker concludes by inviting viewers to join the Heptabase Mastery course, which teaches how to leverage these features as a core PKM system across various workflows.
Key Insights
- The speaker has tested digital PKM systems for over a decade and identifies Heptabase as their all-time favorite tool because it synthesizes the best aspects of multiple competing platforms like Scrintal, Obsidian, Tana, and MarginNote
- Heptabase's PDF highlighting feature allows users to drag and drop highlighted text or area-based annotations directly onto whiteboards, enabling visual representation of connections between different research findings
- The system maintains bidirectional connections where a single highlight can appear across multiple whiteboards, and clicking the info section reveals all contexts where that highlight is referenced
- Users can locate any highlight within its original PDF source with one click, which automatically opens the PDF and scrolls to the exact position where the highlight was created
- The PDF research workflow integrates with daily journaling, allowing users to review past journal entries and discover connections between those notes and research highlights they created
Topics
Transcript
[0:00] I've been testing digital personal knowledge management systems and note-taking apps for over a decade. [music] During that time, one handwriting iPad app really stood out to me, MarginNote. I loved [music] this approach to annotating PDFs, even though it lacked many other features. If you follow me on this channel, you know that Hepta Base has become my all-time favorite PKM tool. It combines the best aspects of so many other tools like Scrintal, Obsidian, and Tana, and I want to add MarginNote to that list, too. [0:32] I've shown this PDF annotation method in one-on-one sessions with many of our Paperless Movement members, lawyers, doctors, and project managers alike, and they immediately saw its potential for enhancing…
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.