In development—
In development
Applied AI
The next product is being formulated. It applies language models to a workflow where the current state of the art is a spreadsheet and a lot of manual reading.
AI applicationWeb
01Products
Built end to end, from the model outwards.
Each product starts as a formulation and ends as something you can install. We build across mobile, web, libraries and APIs — the format follows the problem, never the other way round.
AvailableFirst product · 2026
Broncea
Photobiological dose modelling on a phone
A consumer Android app built on a dosimetric model of ultraviolet exposure. It integrates hyperlocal UV forecasts over time against a personal erythemal threshold, instead of counting minutes against a generic table.
- Platform
- Android
- Languages
- 6
- Accounts required
- None
- Personal data on our servers
- Zero
Broncea is an informational tool, not a medical device, and does not replace professional healthcare advice.
02In the pipeline
Three products in formulation.
We do not announce names, dates or features before they exist. What we can say is the class of problem each one addresses, and the stage it has actually reached.
Coming soon—
Planned
Developer tooling
A tool for the parts of modelling work that are still done by hand. Expected to ship first as an open-source library, then as a hosted service.
Developer tool · Open sourceLibraryAPI
Coming soon—
Planned
Decision systems
An optimization product for operational planning — the class of problem where a two per cent better schedule is worth more than any interface.
Optimization · Web platformWebAPI
03Formats
The shape of a product is a decision, not a default.
A model can reach its user as an app, a library, an endpoint or a report. Choosing wrongly here wastes more effort than any implementation detail.
AI systems
Mobile applications
Web platforms
Mathematical software
Data science tools
Research projects
Open-source libraries
APIs
Developer tools
Simulation & modelling
Decision systems
Commission a product
Have something that should exist?
If you have a problem where the answer needs to be computed rather than looked up, we would like to hear about it — including the constraints that make it awkward.