Most new formulations are variations on old ones. The fastest experiment is the one you find in the archive instead of running again.
All Chemicals & Materials →
AI formulation search lets a chemist describe a target, such as a coating with a given gloss, cure time and VOC limit, and see the closest formulations your company has ever made, what they achieved in testing and why they were dropped. It then suggests the next experiments most likely to close the gap, ranked with their uncertainty. The chemist chooses what to run, and every result goes back into the record.
It works for coatings, adhesives, polymers, lubricants, personal care and agrochemical formulations alike, because the method is the same: join recipes, raw-material data and test results into one record, then search and model over it. Suggestion methods range from similarity search and property models to Bayesian optimisation, chosen to fit how much data you have.
properties, limits, cost
nearest past formulations and results
expected performance with uncertainty
restricted substances, suppliers, cost
what to make and test
every test improves the next round
It is the use of machine learning on formulation records and test results to find relevant past work, predict how a new recipe will perform and suggest which experiments to run next. It shortens the path to a target by making each experiment more informative. It does not remove the need to make and test the formulation.
Less than people expect for search, and more for prediction. Searching the archive is useful from day one. Property models and optimisation need a few dozen well-recorded experiments in a given family to beat a chemist’s intuition, and they improve with each round. We check your data on a sample before promising anything.
The same method applies to cosmetic formulation, with extra constraints: ingredient restrictions under EU Cosmetics Regulation 1223/2009, stability and preservation requirements and claims substantiation. The system can filter and suggest within those rules. The safety assessment and product information file remain the responsible person’s.
What we built, what stage it is at, and a link to the live thing wherever there is one.
yourOS is an operating system with an AI at its heart. You talk to it like a person, out loud or typed. It makes your calls, plans your days and works on your projects with a crew of agents, on your own private server. Our own product, built from the first commit; the waitlist is open.
Website, backend and app assets for Sonora, a free AI sound-therapy app on iOS and Android published by Cognitive AI.
Brand, website, prototype, apps on five platforms, the AI backend and the algorithm-intelligence pipeline for Podswap, a social growth engine that runs without a human in the loop.
In closed beta: Roxy, a private AI assistant with permanent memory running on infrastructure the user owns. Brand, site, product, backend and conversational design.
Live at coherence.com: brand identity generated with AI agents we directed, the motion system and website for the group behind Sonora, AboutAI, WakeUp and MudShadows. Agent work remains in build.
Live at domainbooth.com for DomainBooth, a premium domain brokerage: a new animated mark, every page redesigned and rebuilt with designed mobile layouts, and a custom CMS for its sales record, featured names, press and enquiries.
Bring a formulation family and its test history. We will show what the archive already knows.
30-minute technical call · no deck