The second brain concept has been around for a while. Capture everything. Organize it. Build a system outside your head that remembers what you can't.
It works for humans because our memory is unreliable. We forget context. We lose the thread. A good notes system means you can pick up where you left off.
AI has the same problem.
Every session starts fresh. The model doesn't know what you decided yesterday. It doesn't know why you structured things the way you did. It doesn't remember the three approaches you tried that didn't work.
So you explain it again. And again. And again.
The fix is simple. Build a second brain for the AI.
Save context as you work. Not for yourself. For the model. What you decided. Why you decided it. How things connect. What's left to do. Keep it in markdown files in your project. Plain text the AI can read.
Next session, it picks up where you left off. No re-explaining. No lost context. The conversation continues instead of restarting.
This matters more as projects get complex. The codebase grows. The decisions stack up. The stuff in your head becomes impossible to transfer in a single prompt.
But a collection of markdown files? That transfers instantly.
The AI reads your notes the way a new teammate would read documentation. Except faster. And without complaining that the docs are out of date.
The human second brain is about offloading memory. The AI second brain is about maintaining continuity. Same concept. Different purpose.
Build the system. Save the context. Let the AI remember what you'd have to re-explain.