Design partnerships are open — we embed forward-deployed engineers to build your first environment against a real workload.

Start a pilot →

CASE STUDY · JUN 20, 2026

Insurance agents, proven against the systems they operate

Harper Insurance (YC) trains and evaluates production insurance agents against the actual systems they work in.


Harper runs agents inside real insurance workflows — the kind of work where a wrong action has a dollar value and "it usually works" does not clear the bar.

Their agents train and evaluate against environments built from the systems they actually operate. Success criteria come from Harper's own definition of done, and the adversarial pass attacks the reward before the agent can. What ships is a policy with the evaluation that judged it attached.

A detailed write-up, with results, is in progress with the Harper team.

Work with us

Bring an agent and a goal.

We are taking a small number of design partners. The bar is a real workload, not a logo. Everything runs on your hardware, and you keep the machine.