Where MASS makes a difference
We started with education research because that's where video is richest, yet so slow to turn into findings. Hours of classroom footage can mean weeks of manual coding. MASS was built to change that. And the workflow generalizes: if activity happens on camera, MASS can turn it into data.
Education research: Insight into how students learn
Classroom video captures everything: engagement, collaboration, confusion, breakthroughs. The problem has never been the data; it's the weeks of manual coding between recording and analysis. MASS compresses that to hours, without compromising rigor.
- Engagement & participation: Understand how engagement unfolds across a session and how students move between individual work, discussion, and group activities
- Group-work dynamics: Code who collaborates with whom, when discussion starts, and how roles shift within groups
- Teacher-student interaction: Capture questioning patterns, one-on-one support moments, and whole-class facilitation
- Cross-session comparison: Line up the same activity codes across classrooms, conditions, or points in the semester
- Methodological rigor: The review workflow mirrors second-coder practice, and every AI suggestion is human-approved and audit-logged
MASS grows out of ongoing learning-sciences research at the MLTI Lab. Explore the research behind MASS, from the studies that shaped the tool to published work.
Read the publicationsFrom a single researcher to a whole institution
Research teams
Run multi-coder studies with built-in role management, conflict-free collaborative coding, and a review cycle that maps to your inter-rater process. Your whole pipeline, from raw footage to shareable timeline, lives in one place.
Schools & districts
Support instructional coaching and professional development with evidence instead of anecdotes. Review lesson recordings with clear, visual summaries of classroom activity, and share them securely with the people who need them.
Labs & graduate programs
Give students a rigorous, modern toolchain for observational methods. The AI assist lowers the cost of getting started; the audit trail and review workflow teach good methodology by default.
The same pipeline, any field of view
Annotate subjects, track activity over time, visualize the result. That loop is domain-agnostic. Here's where else we see it fitting.
Usability & UX research
Code participant behavior in usability sessions (hesitation, navigation paths, moments of friction) and compare patterns across participants on one timeline.
Behavioral & developmental studies
Observe interaction, play, and social behavior with frame-accurate coding and multi-subject tracking built for long observational sessions.
Sports & movement analysis
Track players or athletes through a session, code plays and phases of activity, and review the structure of a game or training block at a glance.
Workplace & process studies
Analyze workflows, ergonomics, and team coordination from observational footage. Quantify how work actually happens versus how it's documented.
Animal behavior
Code ethograms from field or lab video: track individuals, mark behavioral states, and visualize activity budgets across hours of recording.
Your use case
If your research question lives in video — any subject, any activity, any setting — the MASS workflow likely fits. Tell us what you're studying.
Does your study fit?
Tell us about your footage and your research question. We'll tell you honestly whether MASS is the right tool, and show you if it is.
Start the conversation