See where your content loses people and why

Facial expression recognition and behavioural analytics that tell you exactly which section of your content is failing, whether that's a recorded meeting or a live learning module.

engagement_stream.live
--
Engaged
baseline calibratingframe 0
The Problem

Your training is a black box

Completion rates tell you someone finished. They tell you nothing about whether they were actually engaged, where they checked out, or why.

Completion rates lie

Someone can complete a training module while mentally checked out for 80% of it. You'd never know.

Surveys are lagging

Post-session surveys capture what people remember feeling, not what actually happened moment to moment.

Zero content-level insight

"Learners are disengaged" is useless. You need to know which slide, which segment, and what the emotional pattern looked like before they quit.

Products

Three ways to understand engagement

Whether you're reviewing a recorded session, tracking live learners, or deploying somewhere facial analysis isn't permitted, Emotuit gives you the engagement data that completion rates never will.

Analyse

Upload a Zoom recording, meeting, or any video of a live session. Get a full engagement breakdown with AI-powered coaching suggestions on exactly what to change.

  • Upload any meeting or session recording
  • Per-participant engagement scoring
  • Transcript aligned to engagement drops
  • AI coaching tied to specific moments
  • Interactive timeline dashboard + PDF report
Learn more

Learn

A lightweight SDK that integrates with your LMS or learning platform. Real-time engagement tracking that shows you exactly where your content fails and why learners drop off.

  • Real-time webcam-based engagement tracking
  • Per-section content effectiveness scoring
  • Drop-off point identification
  • Disengagement prediction before they leave
  • Works with any LMS, SCORM, or xAPI platform
Learn more

Signals

Engagement analytics with no camera at all. Behavioural telemetry only — deployable in EU workplaces and education institutions, where facial analysis is prohibited under the AI Act.

  • No camera, no biometric data
  • Tab-switch, focus and dwell tracking
  • Content-level engagement heatmaps
  • Anonymous mode — zero personal data
  • Outside EU AI Act Article 5(1)(f)
Learn more
Guides

Written for people who have to decide

Long-form, sourced, and updated. The compliance guides in particular cover ground almost nobody else in this market is addressing.

Research

Every component peer-reviewed

Originally designed in 2014. Every architectural decision independently validated by published academic research.

Baseline Calibration
Confirmed as best practice for affective computing. "Calibration involves capturing a neutral expression and adjusting subsequent data accordingly."
Frontiers in Psychology, Jan 2026
Tab-Switch Tracking
Single most important predictor of disengagement in online learning, outperforming self-regulation and satisfaction.
ScienceDirect, 2024
Multi-Signal Fusion
Combining facial expression with behavioural signals improved classification accuracy from 91.5% to 94.6%.
OUCI/DNTB Online Learning Study
Predictive Labelling
73.3% disengagement prediction accuracy with 40% of the session still remaining.
Boote, Agarwal & Mostow, 2021
Content Correlation
Real-time framework mapping facial engagement to content positions for per-section analysis.
PMC MOOC Framework, 2021
Emotion Classification
Deep learning models using identical 7-emotion engagement indices to classify learner states.
PMC / Springer, 2022
Privacy

No facial data leaves the device

All detection and classification runs client-side in the browser. Only numerical scores are transmitted. Never images. Never video.

Client-side inference

TensorFlow.js and ONNX Runtime Web. All processing in the user's browser.

No images transmitted

Only emotion vectors and engagement scores leave the device. Never pixels.

Explicit consent

Webcam requires clear opt-in. No background activation. No exceptions.

Fully anonymisable

Content-level analytics work without any PII whatsoever.

Air-gap compatible

Zero external dependencies. Runs fully offline and on-premise.

Compliance ready

GDPR, institutional governance, governmental data handling. From the ground up.

Pricing

Simple, transparent pricing

No hidden fees. Pick the model that fits how you work.

Analyse

Pay per analysis

One-off cost per recording. Upload a meeting or session video, get the full engagement report and AI coaching. No commitment.

  • Per-participant engagement scoring
  • Transcript-aligned insights
  • AI coaching suggestions
  • Downloadable PDF report
Get a quote

Learn

Monthly per seat

Upfront integration cost plus a monthly per-user fee. Real-time engagement tracking across your entire learning platform.

  • SDK integration and setup
  • Real-time engagement dashboard
  • Content effectiveness scoring
  • Disengagement prediction
Get a quote

Enterprise

Volume pricing

For large-scale deployments where per-seat doesn't make sense. Custom pricing based on your organisation's size and needs.

  • Volume-based pricing
  • Dedicated onboarding
  • On-premise deployment option
  • Custom integrations
Talk to us
FAQ

Common questions

The things people ask before they get in touch. If yours isn't here, just email us.

How is this different from completion rates?
A completion rate tells you someone reached the end. It cannot tell you whether they were paying attention on the way. Compliance training routinely records 90%+ completion while producing little measurable behaviour change. Emotuit measures attention continuously and maps it to the exact section of content being viewed, so you get a specific fix list rather than a single pass/fail number.
Does Emotuit work with our LMS?
Yes. Emotuit Learn is a JavaScript SDK under 50KB that drops into any browser-based learning platform with a single script tag. It works with any LMS, SCORM package or xAPI platform, and requires no migration or infrastructure change.
Is any facial data stored or transmitted?
No. All face detection and emotion classification runs client-side in the browser using TensorFlow.js or ONNX Runtime Web. Only numerical engagement scores leave the device — never images, never video. Webcam access requires explicit opt-in consent, and content-level analytics work with no personally identifiable information at all.
Is engagement tracking legal under the EU AI Act?
Article 5(1)(f) of the EU AI Act prohibits AI systems that infer emotions from biometric data in workplace and education contexts. Emotuit's behavioural signal layer — tab-switching, focus loss, dwell time and window state — does not rely on biometric emotion inference and is designed to be deployable where facial affect analysis is not permitted. Organisations deploying in EU workplace or education settings should confirm their specific configuration with their own legal counsel.
How accurate is facial emotion recognition?
Published studies place multi-signal engagement classification at roughly 94.6% accuracy when facial expression is combined with behavioural signals, compared with 91.5% for facial expression alone. Emotuit uses per-user baseline calibration so readings are measured as deviation from that individual's neutral expression rather than a population average, which reduces error from facial morphology and cultural variation in expression intensity.
Can Emotuit run on-premise or air-gapped?
Yes. The pipeline has zero external network dependencies and can run fully offline and on-premise, which makes it deployable in government, defence and other environments where cloud tools are not permitted.
Get Started

See what completion rates can't tell you

Find out exactly where your content works, where it fails, and what disengagement looks like before people leave.

Request a Demo