← All case studies
EducationFine-tuned private models

A marking assistant that stays inside the campus network

A department needed marking support but could not send student work to a third party. We tuned an open-weight model and deployed it on their own hardware.

11 hrs
Saved per marker weekly
0
Data leaving campus
96%
Agreement with markers
Problem

The constraint came before the requirement

A business school department marked 1,400 scripts a term across six modules. Marking support was welcome; sending student work to a hosted model was not permitted under their data policy, and no exception was going to be granted.

Approach

Open weights, tuned on their own rubrics

We tuned an open-weight model on four years of marked scripts and the department rubrics, deployed on two GPUs in the campus data centre. It drafts rubric-aligned feedback and a provisional band; the marker confirms or changes both, and the change becomes training signal for the next cycle.

Evaluation

Measured against double marking

Before rollout we ran the model against 300 scripts already double-marked by staff. Band agreement with the human markers came out at 96%, within the range the two human markers agreed with each other.

Result

Markers writing less, judging more

Marking time fell by around eleven hours per marker per week, mostly in drafting feedback rather than deciding grades. No student work has left the campus network, which was the condition the project had to meet before anything else counted.

Before / after
Marking hours weekly
198
Feedback turnaround
15 days6 days
Data leaving campus
n/aNone
Band agreement
n/a96%

We were told this was impossible under our data policy. It turned out to be a deployment question, not a policy one.

ABHead of Department, Ashbourne Business School