Mesocort AIGet in touch

Predicting humansunder pressure

We study the fast, pre-verbal layer of human behavior — turning measurable reactions into intelligence that helps people and systems perform when it matters most.

How it worksTalk to our team

Loading interactive brain

Understanding human behaviour before conscious decisions emerge

We are building AI models that learn how people react in the first moments after a stimulus, how that reaction develops into a conscious decision, and what they are likely to do next.

  1. Low-road reactions

    0 ms

    External stimulus

  2. ~250 ms

    Initial response

    Transition between low-road and high-road

  3. ~600 ms

    Behavioral adjustment

  4. High-road reactions

    ~800+ ms

    Conscious decisions

Low-road reactions

Transition between low-road and high-road

High-road reactions

We aim to predict not only what a person will do, but how the response emerges over time.

Millions of realhuman decisions.

Every AI today models the part of the brain that reasons. We model the part that reacts — the fast, pre-verbal layer nobody is building. Read straight from gameplay telemetry at 64 Hz, resolved to 15 ms.

5,500+

years of cumulative
human activity

Capturing decisions and reactions under pressure.

Abstract blue and turquoise data visualizationLearn more about dataset
1,300,000+

Gigabytes ofbehavioral data collected

12,000,000+

People representedin our datasets

64 Hz

Telemetry granularitydown to 15 ms

Initial results that
move the baseline.

We trained Ember and Orbit — the first models built to predict fight-or-flight outcomes — and benchmarked them against leading open-source and frontier LLMs over 1,000 predictions. They are more accurate, orders of magnitude faster, and orders of magnitude cheaper — because they read behaviour directly from telemetry instead of reasoning over text.

ModelAccuracyAvg. time / predictionCost / 1,000 predictions
EMBER by Mesocort AI73.5%0.01 ms$0.000002
ORBIT by Mesocort AI71.2%0.34 ms$0.000062
Qwen 3.5 9B63.5%2.58 s$2.33
Gemini 3 Flash62.7%4.27 s$10.16
GPT 5.461.6%8.97 s$48.72
DeepSeek V4 Pro58.9%0.91 s$10.66
Majority-class
baseline51.5%——

Best-performing configuration shown per model family. LLM results measured over 1,000 predictions; Orbit & Ember over the full validation set. Full methodology in our scientific paper (under review, available under NDA).

Grounded in research,
built in the real world.

We work with top researchers and research institutions.

Centaur AI

Human cognition foundation model

Marcel Binz, PhD — Author of Centaur, the foundation model of human cognition, who reviewed our scientific paper.

Masaryk University

Psychology of digital behaviour

Prof. David Šmahel — Joint research on esports athletes, pairing in-game and physiological data during competitive play.

VŠB — Technical University of Ostrava

AI research & PhD talent

Prof. Ivan Zelinka — Among the top 2% most-cited AI scientists worldwide: swarm intelligence and evolutionary computing.

Centaur AI

Human cognition foundation model

Marcel Binz, PhD — Author of Centaur, the foundation model of human cognition, who reviewed our scientific paper.

Masaryk University

Psychology of digital behaviour

Prof. David Šmahel — Joint research on esports athletes, pairing in-game and physiological data during competitive play.

VŠB — Technical University of Ostrava

AI research & PhD talent

Prof. Ivan Zelinka — Among the top 2% most-cited AI scientists worldwide: swarm intelligence and evolutionary computing.