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.

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.