Pachinko pachinko
Pachinko pachinko
Design Notes on Useful AI

privacy / note 06

Can I keep some things private?

Wanting AI help doesn't mean handing it everything. The product's job is to make what it reads visible, and what it must not read untouchable.

Privacy is an interface control.

A project that should stay private shouldn't end up as accidental context for a chat, a feed, or some outside tool.

No fence, no real work.

Get privacy wrong and users leave the same week. The ones who stay hold back: the sensitive project lives in another app, the real numbers never get pasted in, and the AI only sees the harmless stuff. An assistant nobody trusts never gets the material where it could actually help.

What to build.

Show the scope at the moment of asking: a visible list of what the model will read. Make exclusion a first-class control you can reach from the thing itself: hide this project, this folder, this account. Start new AI features with the narrowest scope that works and make widening it deliberate. A narrow scope costs a rerun. A leak is permanent.

design principle

Show the active scope before the output, and let users fence off what is out of bounds.

one implementation

Pachinko's version: chat uses the notes you select. MCP clients discover visible workspace data. Any project can be marked Hide from AI with a right click, keeping it out of automatic AI browsing and MCP lists unless you explicitly provide its notes as context.