Education & eLearning

An adaptive learning platform with a curriculum-grounded AI tutor

We added adaptive practice and a generative AI tutor to an online learning platform, grounding every answer in the provider's own curriculum content and keeping teachers in control.

more practice sessions completed per active student
27%more practice sessions completed per active student
of sampled tutor answers rated correct and on-syllabus by teachers
92%of sampled tutor answers rated correct and on-syllabus by teachers
from discovery kickoff to first cohort launch
16 wksfrom discovery kickoff to first cohort launch
A child learning online on a laptop at home

The challenge

The provider offered recorded lessons and fixed practice sets for secondary school maths and science. Every student saw the same questions in the same order, so strong students were bored and struggling students fell behind without anyone noticing until test results arrived.

Students also wanted help outside live class hours. The team was interested in a generative AI tutor but was rightly cautious: answers had to match the syllabus, avoid simply handing over solutions, be appropriate for minors, and be reviewable by teachers and parents.

Our approach

We ran a six-week discovery and MVP phase with one subject and two grades. Each practice item was tagged to curriculum learning objectives, and a knowledge tracing model estimates mastery per objective from student responses. The practice engine then selects the next item to target weak objectives while mixing in review of earlier material.

The AI tutor uses retrieval-augmented generation over the provider's own lesson transcripts, worked examples and textbook content. It is instructed to guide with hints and questions rather than give final answers, cites the lesson it drew from, and declines off-topic requests. Inputs and outputs pass through moderation, and conversations are logged for teacher review.

Before launch we built an evaluation set of several hundred real student questions graded by subject teachers for correctness, pedagogy and tone, and used it to compare prompt and retrieval changes. Teachers see a dashboard of mastery by objective and can flag tutor responses, which feed back into the evaluation set.

What we delivered

  • Curriculum-tagged item bank mapped to learning objectives
  • Knowledge tracing to estimate mastery and adapt practice sequences
  • AI tutor grounded in the provider's lessons with source citations
  • Hint-first tutoring behaviour with moderation and topic guardrails
  • Teacher dashboard for mastery, at-risk students and flagged conversations
  • Teacher-graded evaluation set used to test every tutor change

More case studies

Travel & hospitality

A complete taxi booking platform: fleet ERP, booking website and Flutter apps

We built a taxi operator's full digital platform: a fleet and operations ERP, a booking website, and Flutter rider and driver apps sharing one real-time backend.

ERP, website and mobile apps on one live backend
3-in-1ERP, website and mobile apps on one live backend
apps for iOS and Android from one Flutter codebase
2apps for iOS and Android from one Flutter codebase
driver tracking for riders and the dispatch team
Livedriver tracking for riders and the dispatch team

Travel & hospitality

A restaurant management platform: ERP, online ordering website and Flutter apps

We built a restaurant group's ERP for orders, kitchen, menu and inventory, plus an online ordering website and a Flutter customer app, all on one shared system.

ERP, website and mobile app sharing one menu
3-in-1ERP, website and mobile app sharing one menu
commission on direct online orders
0%commission on direct online orders
sales and stock view across every outlet
Livesales and stock view across every outlet

Healthcare & life sciences

A remote patient monitoring platform that care teams actually use

We rebuilt a telehealth provider's video visit and remote monitoring stack so device readings, alerts and clinician workflows live in one HIPAA-aligned platform.

faster median time from out-of-range reading to clinician review
64%faster median time from out-of-range reading to clinician review
systems clinicians use to review a monitored patient
3→1systems clinicians use to review a monitored patient
to launch a new chronic care programme, down from months
11 wksto launch a new chronic care programme, down from months

Facing a similar challenge?

Tell us where you are and what you need. A senior engineer replies within 24 hours with next steps, not a sales script.