Most AI second brain setups fail because the vault isn't built for it. This covers the structure, linking scheme, and agent protocol that actually make it work.

There's been a lot of excitement recently around building a 'Second Brain' using Claude and Obsidian. Unfamilliar? Read my Claude Code or Obsidian Guides. Just make sure you come back and finish this article after :) For those who missed it, this idea was popularised by Andrej Karpathy and involves building a Wikipedia-style set of interconnected notes which can then be navigated and searched by AI agents. This means that we don't have to provide AI agents the same context ov

Most prompts don't need examples. This explains what few-shot prompting does, why examples help models, and when to actually reach for them.

I built an AI-powered task system in Obsidian using custom Claude Code skills. This covers context engineering, note types, and the morning briefing automation.

"You're an expert X." "Act as a Y" Role prompting is one of the most widely repeated tips in AI circles. The underlying idea is that if you assign the model a job title or area of expertise, it will respond more like a person who holds that role, making it more relevant, more precise, more expert-sounding. The research on whether that actually holds up is more nuanced than the advice suggests. And the nuance is important if you want to try this out yourself. What is role prom

AI models struggle to recall information in the middle of long documents. It's a positional bias called the Lost in the Middle Effect. Here's how to fix it.

Tokens are how AI measures text. Context windows are working memory. When they fill, earlier content disappears. Here's what that means and how to manage it.

Claude Code works directly on your files, runs code, and manages tasks without you needing to be a developer. Here's what you need to know to use it well.

Skills are reusable instruction sets for AI agents - write once, the agent uses them on demand. Covers structure, loading logic, security, and authoring tips.

Write Once, Use Forever. Think about the last time you explained your workflow to a new hire at work. You probably didn't just hand them a list of tools and wish them luck. You walked them through the process, explained why things work the way they do, and maybe showed them an example or two. Three weeks later, they're flying solo. AI can't do that. At least not out of the box. Every conversation starts from scratch. There's no memory of how you like things done, no recollect

MCP servers let your AI agent read from and act on external services without manual copy-pasting. Covers setup, authentication, and when to build your own.