Realm
A model of how matter behaves, built from measurements.
Realm is trained on every result from Robosynth, Robolab, Biopen and Control. Ask how a material ages, what is in a food or how a microbe responds, and it answers from measured data with a confidence score.
Three ways to query Realm, each priced per query.
For agents
Application programming interface and agent server
A Model Context Protocol server, so agents can query Realm directly.
For people
Search and ask
Ask in plain English in the Wallace App or on the web. Answers show confidence and source measurements.
In your tools
Plug-ins
Realm inside computer-aided design software, lab notebooks and a Python library.
If Realm has no data for a question, it queues a Robolab experiment. The result answers the question and is added to Realm.
Train your own model on Realm data.
Secure training
Outside labs train their models inside Wallace’s secure environment. Trained models and results leave. The raw data stays with Wallace.
Benchmarks
Score scientist models against measured physical results.
Discovery partnerships
Make a discovery using Realm and share in its commercial value.
What happens when you ask Realm a question.
Ask Realm a question.
Measured questions get an answer with a confidence score. Unmeasured questions queue a Robolab experiment.
Pick an example or type your own question.
01
Ask
An agent or person queries Realm.
02
Run
No data yet? Robolab runs the experiment, staffless.
03
Capture
A signed result, plus the full capture of the run.
04
Learn
Realm updates on the new physical data.
05
Design
Realm chooses the most informative next run.