Callback

Remember what you learn.

Talking to Claude is a remarkably good way to learn something. It's a terrible way to remember it. Callback closes the loop: it turns your conversations into quiz questions and pings your phone with each one right before you'd forget it — so what you learned this week is still yours next year.

invite-only beta  ·  hello@callback.cards

How it works

1

Learn something

Talk to Claude the way you already do — any topic, any depth, until it makes sense.

2

Say quiz me on this

Claude distills what you worked through — the things you asked about, struggled with, were surprised by — into a handful of well-formed questions, and runs a quick first pass on the spot.

3

Answer your phone

The app pings you when questions come due. Miss one and it returns sooner; master it and it stretches out — each review timed to land just before the memory fades.

Why it's different

The cards write themselves

The classic reason people abandon flashcards is authoring. Here the tutor who just taught you writes the questions — from the conversation you actually had, not a generic deck.

Real recall, really graded

Typing an answer from memory beats recognizing one in a list — but ordinary apps can't grade prose. Claude grades yours semantically, so free response is the default, not the fallback.

The tutor stays in the loop

A question you keep missing doesn't just keep coming back. It goes back to Claude, which re-teaches the idea from a fresh angle and writes a better question. Failure is a teaching problem, not a scheduling problem.

The science

Retrieval beats re-reading (the testing effect) · spaced beats massed (the spacing effect) · scheduling by FSRS-6 at a 0.90 retention target · first review lands the next day, not next month · new cards drip, topics interleave, leeches get re-taught