Canvas & Ratio
Choose your destination platform format
Layout Template
Choose a content structure for your slides
Preset Themes
Typography & Sizing
Brand Kit Customization
AGENCYConfigure brand assets for headers & footers
Outro Slide CTA
Customize your closing call-to-action slide
Background Pattern
Build Your Carousel
Drag and drop any post card below onto a slide, or use the quick buttons to insert content/images instantly!

Iβve been testing an agent-only @obsdmd vault in parallel with my Zettelkasten. My expectation: a faster way to surface sources worth reading. What I found: it could do so much more than that. A few findings π


1/ It looks like a Zettelkasten The @karpathy LLM-wiki does what you'd expect β digests sources, chunks them, synthesizes answers. But the structure mapped almost one-to-one to the Zettelkasten I've been teaching for years. It just does the grunt work automatically. Maybe more people can get the benefits without the years of system-noodling it usually takes? There's just one thing missing though...


2/ No place to see my ideas grow The system captures everything (synthesis, connections, patterns). But my thinking ends up mixed in with the agent's output. There's no place where I can see just my ideas, review them, and build on them. It's all in there somewhere. Remember that time when you argued with a dead author and won? Good luck finding it.


3/ Luhmann solved this 50 years ago. Thankfully, I didn't have to create anything new. I added what I call the CONVOs layer β a place where only my thinking lives. I reply to authors. They reply to me. Not a wiki β an async conversation applied to problems I want to solve. The agent isn't allowed to write here without checking with me first. Which authors do you want to have a group chat with?


4/ Wiki + CONVO = Publish-ready thinking All the ammoβs there. When an idea hits, examples, stories, and arguments are already in the conversation. Itβs not just a wiki. Itβs a writing tool.

5/ It can evolve with you The CONVO is the playground. But some ideas stop being experiments. When an idea becomes something I live by β my niche, my mission β it graduates to Ops. Ops is the rules the LLM lives by. Whenever it needs context, it knows where to look. I never re-explain myself. And we continuously evolve together. Now... it's not all obsidian butterflies and claud rainbows. There's still a lot of evolving that can happen :) - Not loving how it uses tags - It actually doesn't use its own index - How its search doesn't really scale (echoed by Karpathy himself) If you're on the fence, just create a new vault and put Karpathy's idea file in. You always learn more when you just give it a try. Let me know if you have any questions about starting.
