About
Propab is building the research infrastructure that lets an AI co-researcher work on a real problem for days, with the tools, data and compute a lab would use, and with every result traced.
01
Today’s models can reason about science. What stops them is everything around the reasoning: a sandbox that dies, a dataset that will not download, a tool nobody installed, a check nobody ran. Propab is that missing infrastructure, built to be dependable.
02
Real research does not fit in a chat turn. Propab can work on one problem for days, try hundreds of approaches and run thousands of experiments, and it is never cut short by a step counter. Limits apply to money, compute and time, the things that are really scarce.
03
A fast wrong answer is worse than none. Every number Propab reports opens to the code that produced it, the data it read and the sources it relied on, so you can check it, rerun it or disagree with it.
How we build
Who we are
Propab was founded by Shani Singh. We work closely with the researchers who use it; if you want to shape what it becomes, talk to us.