AI geography marking for schools.
Department for Education · Competition for Innovation winner
Geography teachers get a first draft of their marking, written against their own department’s mark scheme. They edit that draft and approve the grade before a student sees any of it.
Overview
OpenKit won a Department for Education Competition for Innovation award to build a tool that uses generative AI to help teachers assess progress and give feedback on their students’ work. The Department is the customer and the product is ours, and delivery is reviewed against performance targets the Department set at the outset.
Rubrical marks geography alone, because a marking tool has to hold one subject’s mark scheme well enough for a department to defend the marks it produces at moderation. Development is complete and the platform is live in fourteen schools.
- Funded by the Department for Education as a Competition for Innovation winner, delivered under the Department’s governance.
- Every feature signed off by a teacher advisory board before it shipped, with the decisions documented.
- Marking runs behind a trust-wide moderation framework, with service levels in place.
52%
less marking time, reported by teachers in the developer’s tests and recorded by the Department for Education in its schools white paper.
95%
teacher satisfaction with the marking and feedback the platform drafts for them.
2.5x
more detailed feedback than teachers had time to write by hand, against the same set of work.
92%
of marks matched the senior teacher’s grade on held-out GCSE geography responses, against 67% for generic AI tools scored on the same rubric.
Fourteen
schools live with the platform, marking geography from Key Stage 3 to GCSE.
Challenge
What teachers asked for first
When we put a single expression-of-interest call through the geography teaching community, twenty teachers signed up inside a fortnight and eighteen of them named marking and feedback as the thing they most needed help with. Another eighty-two signed up to the two classroom-AI and Rubrical workshops we ran with our teaching partner. The brief set the constraints the platform was built to:
- A teacher signs every grade. The platform drafts against the rubric and stops there.
- The mark scheme the department already uses is the standard the model is held to.
- Anything touching assessed work has to leave a moderation trail a school can produce on request.
Approach
Inside Rubrical
A marking workspace the teacher signs off
The rubric and mark scheme go in, work comes in by upload or straight from Google Classroom or Microsoft Teams, and the platform drafts against each rubric criterion. Nothing reaches a student until a teacher has read it, edited it and approved it.
The PEEC+ analysis framework
A hierarchical model for handling the argument structures in Key Stage 3 to GCSE long-form answers, developed and validated in its own right, then integrated into the marking pipeline. It lets the system read a long-form answer as an argument and mark how the case is built.
A lesson plan generator
Built alongside the marking work because teachers kept asking for the other half of the job, and signed off by the advisory board with the marking interface.
Class-level analytics
Topic-level strengths, gaps and common misconceptions across a class, so a teacher can aim the next lesson at what the class actually got wrong.
Refinements for SEND and EAL
The teacher advisory board asked for these, and they were built and in the product before the first schools marked with it.
A teacher advisory board with a vote
Teachers on the board score what gets built next, and each design decision is written down with the reasoning behind it. Every feature in the platform was signed off through them before it shipped.
Oversight
Nothing reaches a student until a teacher signs it
Approve it, revise it, or send it back
The student’s answer sits on the left and the rubric level, the mark range and the descriptor sit on the right, with a written summary underneath explaining which parts of the answer earned what and where the evidence was missing. The teacher adds their own comment and either approves the assessment or sends it to be revised.
Result
What teachers reported
The figures above come from Rubrical’s own tests with teachers.
The Department for Education records the marking figure on page 98 of its schools white paper, Every child achieving and thriving (February 2026): “Teachers report a 52% reduction in marking time in the developer’s tests.” The same entry records the Department’s initial £1m award in 2024 and a further £1m from Innovate UK.
Status
Where Rubrical is now
Rubrical is in production, and the model is refreshed against new marking data each quarter as the rollout widens.
- Three schools marked two hundred papers a week before the wider rollout.
- The commercial model moved from individual-teacher subscriptions to department-level licensing, because the demand that came back was for whole departments and for Key Stage 3 alongside GCSE.
Stack
What it runs on and the controls around it
The build
- Fine-tuned subject-specific model
- Private RAG
- DfE content store training
- Azure UK tenant
- OAuth via trust IdP
- Google Classroom + Teams integration
- KILN evaluation framework
OpenKit certifications
- ISO 27001
- ISO 9001, UKAS-accredited
- Cyber Essentials
Controls on this project
- Operates to UK GDPR
- UK data residency
- DfE DPIA approved
Other engagements
What could your business do with AI?
Find out with experts who become part of your team. We uncover opportunities, get ideas working, and help your people build on the results. We reply within one working day.
Get in touch AI Audit