A chemistry world model
for formulation intelligence.
It learns how ingredients interact, and predicts how a formulation behaves before anyone touches a beaker.
It doesn't predict the next word.
It predicts the chemical properties.
Formulation R&D still runs on slow, expensive iteration - because the failure modes are coupled physics, not a search space. That takes a model that understands the chemistry, and none existed. So we built all of it ourselves: the architecture, the pretraining, the experimental data underneath.
Arrives already knowing chemistry.
Thousands of formulation runs we generated ourselves.
Learns your ingredients from a little of your data.
World models power the Virtual Instruments that predict your formulation, and the Active Learning loop that sharpens with every experiment you run.
And no - it is not an LLM.
Already running in real R&D.
Not a research demo. Deployed today across formulation-intensive industries, and now extending into biologics.
Suspension stability and rheology
Surfactants, shelf life
Faster reformulation at scale
Viscosity, aggregation, injectability
The world model, in your lab.
Build a formulation, run it against digital twin instruments, see the result in seconds.
Predict, model, optimize.
Thousands of candidates before the lab
Virtual experiments on digital twin instruments
Turn archived experiments into an asset
Adapt it to your ingredients and instruments
It joins the loop you already run.
A science-first approach.
When the Syringe Is the Bottleneck: Viscosity, Protein Stability, and the Physics of Injectable Biologics
12 min readThe Importance of Rheology in Formulation Design
8 min readWhy Waiting Months for Stability Data is Killing Innovation in Formulation Science
5 min readDesigning the Future of Chemical Products with AI, and Not Being Confidently Incorrect
5 min readReady to put the model to work on your chemistry?
See a live prediction run, or talk to us about a pilot.
Partnership and investor enquiries welcome.