How Grasp Maths works

What "adaptive" actually means here — explained honestly.

Every claim on this page describes what the engine does today, not a roadmap. Where something is a genuine limitation, we say so.

The five-stage loop

Diagnose, estimate, detect, repair, confirm.

01

Diagnose

A short adaptive screening test builds a starting picture across the topic — not a fixed set of questions everyone gets the same.

02

Estimate

Every answer updates a per-skill mastery probability using Bayesian Knowledge Tracing, a published statistical model — not a black-box score.

03

Detect

The engine looks for a genuine pattern across several attempts and question types, not a single wrong answer, before calling something a gap.

04

Repair

Practice targets the specific failing skill and its prerequisite — not just "more questions on this topic."

05

Confirm

The repaired skill is re-tested before the plan moves on. Progress is checked, not assumed.

A real, published model

Bayesian Knowledge Tracing, not a secret algorithm.

The mastery probability behind every skill uses Bayesian Knowledge Tracing (Corbett & Anderson, 1994) — decades-old, peer-reviewed learning-science research, applied the same way in classrooms and research studies worldwide. It isn't something we invented, and it isn't a mystery: it updates on four things — whether the answer was right, how consistent the pattern has been, whether the learner has shown it across more than one question style, and whether the skill has held up over more than one sitting.

  • A right answer moves the estimate up; a wrong one moves it down
  • One lucky guess can't fake "mastered" — that label needs a real streak across varied question types
  • Specific error patterns are tagged, not just marked wrong
  • Estimates are never shown as false 100% or 0% certainty
Equivalent fractions Year 4 · Fractions
Mastery probability 56%
Struggling across 3 sessions

Accuracy falls when denominators increase — the engine has spotted the same pattern three sessions running, not just a single bad day.

Recommended next
  1. Repair equivalent fractions
  2. Review multiplication facts
  3. Recheck equivalent fractions
  4. Progress to comparing fractions
What we're honest about

Where this is strong, and where it genuinely isn't yet.

Published, not proprietary

The underlying model is public, peer-reviewed research, not a secret formula. How it decides can be explained in plain English — as it is on this page.

Standard starting parameters

The model currently runs on the commonly-cited generic defaults from the research literature, not parameters fitted to Grasp Maths's own students yet. We're actively logging anonymised per-answer data to calibrate that honestly, rather than claiming a precision we haven't earned.

A tool, not a tutor

The engine finds gaps and recommends the next useful practice. It doesn't replace a qualified tutor's ability to explain, encourage and adapt in person — the two work best together.

Start the journey

Choose a year group and begin with one question at a time.