When your AI saves, is it writing for you or the next AI?
There’s a small difference in how you ask an AI to save something, and it changes what gets saved.
“Save this for next time.” The AI writes a message to the next AI, and it comes out as instructions:
“Next session: confirm the hotel before booking trains. Do not change the Paris dates. Remind the user about the deposit.”
“Save what we settled.” The AI writes down facts:
“Paris is three nights. Trains between cities; a rental car was dropped because of city parking. The hotel deposit is due May 1.”
The second note stays true after the conversation ends. A month later, it still says where things stand and why.
The first is a set of instructions from a moment that has already passed. A new conversation reads them and follows them, even after the plans have changed.
I saw this in my own records.
Notes written as instructions carried an earlier stage into new conversations. Notes written as facts read like a record: what was decided, and why.
Now when I save, I ask for what settled.
Have you noticed how your AI writes the notes it saves? I’m curious what others have seen.
Replies
My agent's notes ended up with both, in a fixed shape: one fact per note, then a line for why, then a line for how to apply it. The fact and the why are your second kind, they stay true. The how to apply is the instruction, and because it sits right under its reason, a later session can see when the reason no longer holds and the instruction should go. One more small rule that matters: dates are written as dates. "Next week" in a note means nothing a month later.