Control Tower and Inspect

Control Tower runs its evaluations on Inspect. Samples go through Inspect's solvers and scorers, against its model providers, inside its sandboxes, and come out as an Inspect .eval log. ct run eval passes its Inspect-facing options straight through, so those options behave the way Inspect documents them.

Nothing below is restated here. Follow the link.

ConcernInspect documentation
Model names, providers, credentialsModels, Providers
Reasoning options, caching, batch APIsReasoning, Caching, Batch Mode
Container sandboxes and their toolsSandboxing, Standard Tools
Time, message, token, and cost limitsSetting Limits
Retries and sample errorsHandling Errors
Concurrency and parallelismParallelism, Concurrency
The .eval log formatLog Files, Dataframes

Coding agents can read all of it directly: Inspect publishes an index at https://inspect.aisi.org.uk/llms.txt and a markdown copy of every page by appending .md to its path.

Everything Control Tower adds on top — settings, main and side tasks, protocols, monitors, safety metrics, trajectories, fleets — is documented in the rest of these docs.