What breaks your AI workflow between sessions?

I built Second Brain because I kept hitting the same wall.

I'd have a really productive session with Claude, talk through an architecture decision, get to a clear conclusion, close the tab. Next day I'd open a new chat and have to explain everything from scratch. Same thing with Cursor. Same thing with ChatGPT. Every tool starts fresh, every time.

After a while it felt less like having an AI assistant and more like hiring someone with amnesia.

So I want to hear from you: what does this actually look like in your workflow? Are you copy-pasting context into every new session? Keeping a running doc you paste in manually? Just accepting the loss and re-explaining?

And what tools are in your daily stack? Claude, ChatGPT, Cursor, Perplexity, something else?

Genuinely curious what the friction looks like for people outside my own head.