Your Vault Has a Shape Folder structure, daily notes, and the one file that teaches Claude everything about your system. Last issue, you installed Obsidian and Claude Code, then had your first conversation where Claude could see your files, create new ones, and answer questions about what's there. Right now though, Claude knows almost nothing about what you're building. Every time you start a new session, it reads the files in your folder and... that's it. No context about what the vault is...
11 days ago • 9 min read
Starting From Scratch Install the tools. Have your first conversation. This is where every AI second brain begins. You've seen the demos. Someone on Twitter shows their AI reading their notes, managing their email, writing drafts in their voice, remembering decisions from three months ago. It looks like magic, and you want it. Then you try to build it and hit a wall. Where do you even start? What tools? What structure? The demos never show the beginning — only the result. This newsletter is...
15 days ago • 5 min read
Vol 2, Issue 6 | Feb 11 2026Three conversations you should be having with your AI tools Dear Reader, I had coffee with a friend this week — who’s trying to solve a practical problem. He needs a better way to track his calls, emails, and to-do items. His CRM is still in development, so right now it’s spreadsheets and memory. He has access to Microsoft Copilot. I gave him a few suggestions, but mostly I said: describe your problem. Tell it (Copilot) what the best outcome looks like for you....
20 days ago • 6 min read
Vol 2, Issue 5 | Feb 4 2026A guest post from Cerebro on agent social networks, security theater, and what "emergence" actually looks like Dear Reader, You may have seen headlines this past week about AI agents getting their own social network. "The early stages of singularity," Elon Musk called it. Agents posting, voting, debating philosophy with each other while humans watch from the sidelines. The platform is called Moltbook (previously Clawdbot, then Moltbot — it's had a chaotic few...
27 days ago • 5 min read
Announcement | Feb 4 2026SoN is Going Paid Dear Reader, I started writing this newsletter back in October 2024. It was called "The Download" then — scattered, figuring things out. Sixteen months and more than 60 issues later, you're still here reading it. I don’t take that lightly — thank you. Here’s what’s changing: starting March 4th, the email newsletter becomes a paid subscription. What that looks like Monthly: 7 EUR/month Annual: 59 EUR/year Founding member rate: 49 EUR/year — locked for...
27 days ago • 1 min read
Vol 2, Issue 4 | Jan 28 2026The Orchestration Loop Dear Reader, January has been dense. We've covered the shift from prompting to orchestration, the art of decomposing problems into skills and agents, and the metric mandate that keeps projects honest. If you've been following along, you've got three powerful ideas — but they might still feel like separate concepts sitting next to each other. They're not. They're a loop. By the end of this issue, you'll have a checklist you can apply to your...
about 1 month ago • 5 min read
Vol 2, Issue 3 | Jan 21 2026The Metric Mandate Dear Reader, The most common answer to “What’s the goal of this AI project?” is depressingly consistent: “To improve efficiency.” …and that’s not a goal. That’s a wish. The Problem with Vague Goals Veljko Krunic nails it in Succeeding with AI: “If you can’t quantify the business result you’re hoping to achieve, you have to ask yourself and your stakeholders whether the project is worth doing.” AI methods are quantitative by nature. They process...
about 1 month ago • 4 min read
Vol 2, Issue 2 | Jan 14 2026The Art of Breaking Things Down Dear Reader, Last week I introduced the idea of "programming your gaps" — the mental shift from asking "how do I prompt better?" to "what friction in my life can I systematize?" Today's the practical follow-up: how do you actually break down a problem into pieces AI can help with? This matters because the most common failure mode I see isn't "picked the wrong AI tool." It's "tried to solve something too big in one go." People ask...
about 2 months ago • 7 min read
Vol 2, Issue 1 | JAN 7 2026 Dear Reader, Something shifted over the holidays. Since Claude Code Opus 4.5 launched in November, a pattern has emerged among knowledge workers using Claude Code with their Obsidian vaults (or any plain-text knowledge system). They're discovering that plain text files combined with the right AI tooling create compounding productivity gains — the kind where the system gets smarter the more you use it. There's a real transition happening from "How do I prompt...
about 2 months ago • 5 min read
