Multi-agent testing and deployment
Shakedown runs your agent teams against stateful copies of the systems they touch, scores the end state with deterministic checks, and replays each step. Control runs the passing teams in production, in any industry.
How we test
Each system joins through a connector: an ERP, a plant, a database, a simulated supplier hub. Each run gets fresh copies.
Databases, files, queues and the world clock save at one step. Systems without exact saves replay from a seed.
The scenario schedules faults on the world clock: a machine alarm at 7:40, a supplier delay at 9:15, a rush order at 1:30.
Up to four agent setups, N runs each, interleaved so no setup gets easier conditions. Limits hold in the environment, and denied calls count.
Deterministic goal and safety checks read the final state. Each pass rate ships with a 95% Wilson interval.
Engine
Each connector declares exact save or replay. Branch any run at any step.
Goal and safety checks run as code against the end state.
Up to four setups, interleaved runs, pass rates with a 95% interval.
Purchasing caps and approval gates hold outside the agent. Denied calls count.
The platform
Environments composes worlds from connectors. Shakedown runs experiments and suites in those worlds. Control runs agents in production with the same event format.
Experiments and suites: setups side by side, pass rates with intervals, regressions flagged between runs.
Worlds composed from connectors, saved after each step with a state change, restored exactly or by replay.
A live board for agents in production, with provenance on each status and raw events behind each summary.

Get started
One workflow, one world, a few hundred runs. You leave with traces, intervals and a suite to rerun on each change.