Brainback
researchdata

How we measure effort without watching

Effort signals that don't require surveillance.

Jun 15, 20265 min readBrainback Research
abstract

The metrics that predict learning aren't the ones you'd expect — and they don't require watching the student.

Effort is famously hard to measure. Time spent is a proxy but not a great one; a student can leave a tab open. Attempts submitted is better but rewards volume over quality. Hints used is misleading — a student might be avoiding hints because they lack points, not because they didn't need help.

The metric that survives the most scrutiny is a composite: attempts × explain-back score × recall streak length. A student who attempts, explains back well, and maintains a recall streak is a student who is genuinely engaged. Any two of those without the third is a warning sign.

We use this composite to compute the daily effort score visible on the parent dashboard. It doesn't require watching the student. It doesn't require tracking mouse movement or eye position. It just requires that the student actually do the workflow — which the workflow itself enforces.

The privacy stance and the measurement stance align. That is not an accident. That was the design.


Written by Brainback Research. Published Jun 15, 2026. Filed under Data.

if this landed, share it with the friend who’s outsourcing their brain

if the research landed

Put it into practice this semester.

Every essay here is downstream of a design decision inside Brainback. Come see the design.