evals, retraining, and reality: field session

​evals, retraining, and reality
post-deployment physical AI

​a policy that worked in the lab meets a customer's floor. the lighting changes. an object shows up that no one collected data for. this is the moment where most of the real work in physical AI lives. durable value sits here: in the evals, the failure data, and the loop that turns every deployed hour into the next training cycle.

​boundless and qualcomm are hosting a closed technical session for founders and operators deploying physical AI in India. how do you verify a robot once it's live? what do you do with failure data? how do you close the retraining loop? a few operators open with where their deployments stand. then the rest of the group takes over

​22 october, 5:30 pm. localhost, koramangala.

​15 seats.