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.
| Concern | Inspect documentation |
|---|---|
| Model names, providers, credentials | Models, Providers |
| Reasoning options, caching, batch APIs | Reasoning, Caching, Batch Mode |
| Container sandboxes and their tools | Sandboxing, Standard Tools |
| Time, message, token, and cost limits | Setting Limits |
| Retries and sample errors | Handling Errors |
| Concurrency and parallelism | Parallelism, Concurrency |
The .eval log format | Log 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, such as settings, main and side tasks, protocols, monitors, safety metrics, trajectories, and fleets, is documented in the rest of these docs.