About Us
Clear evidence. More confident decisions about AI.
At Dry Run, we help schools and education technology teams understand how AI products perform in practice—not just what they promise. When AI influences learning, feedback or assessment, its behaviour matters. Our purpose is to give the people building and choosing these tools clearer evidence to support their decisions.
Our Approach
We test AI against realistic education scenarios, focusing on accuracy, fairness, feedback quality and meaningful human oversight. We explain what we tested, what we found and where uncertainty remains. When a product changes, targeted retesting helps teams understand whether previous findings still hold.
Who we are
The People Behind Dry Run
Tanveer
Senior Software Engineer
[Two or three sentences. Where you’ve worked, what you’ve shipped in education or health, why interface-level oversight is the part you care about. Concrete beats impressive — name real products.]
Andrea
Product Lead
[Two or three sentences. Systems you’ve built, evaluation and observability work, why reproducibility is the thing you won’t compromise on. Name real systems.]
Irum
English Educator
[Two or three sentences. Where you’ve worked, what you’ve shipped in education or health, why interface-level oversight is the part you care about. Concrete beats impressive — name real products.]
Raza
AI Assurance Product Designer
[Two or three sentences. Systems you’ve built, evaluation and observability work, why reproducibility is the thing you won’t compromise on. Name real systems.]