Control Tower Documentation

Control Tower is an AI control evaluation framework for measuring the effectiveness of safety protocols when deploying potentially misaligned AI agents. It provides realistic software environments where AI agents complete tasks while safety protocols monitor for malicious behavior, and models AI control as a game between a Blue Team (maximizing usefulness and safety) and a Red Team (attempting to subvert safety measures).

Where to start

Running evaluations on existing settings: start with the Quickstart, then the User Guide covers running evaluations, monitoring, viewing trajectories, and measuring safety and usefulness.
Building settings and tasks: start with the Hands-On Guide, then the User Guide covers environments, porting a benchmark, main tasks, side tasks, scorers, sabotage trajectories, and protocols.

Both paths use the objects defined in Core Concepts; the Glossary spells out every abbreviation. To change Control Tower itself, see CONTRIBUTING.md.

Stability

From v6.0.0, only a major release makes a breaking change, and a breaking change is a change to the stable API:

the ct run, ct runs, ct settings, ct protocols, ct live and ct login commands, as the CLI reference lists them;
the Python API this documentation describes, including the Python reference;
the eval log format;
the env API setting packages build on (ct-setting-sdk and its wire protocol), versioned on its own: only an SDK major changes it incompatibly.

ct extras and the modules behind it, control_tower.extras and control_tower.datasets.importers, are not part of the stable API and can change or move in any release.

User Guide

Basics

Page	Description
Quickstart	Fresh machine to running evals on public environments with an OpenRouter key
Hands-On Guide	Build a toy environment and run your first eval
Web Viewer	View uploaded trajectories and eval results

Concepts

Page	Description
AI Control Concepts	Understand the core framework
Core Concepts	Every object Control Tower works with, what it is in code, and where it is documented
Architecture at a Glance	See how settings, environments, tasks, samples, trajectories, and matches fit together
Control Tower and Inspect	Which behaviour comes from Inspect and is documented there

Running

Page	Description
Running Evaluations	Run evaluations with policies, task selection, batching, and replay
Control Evals	Run an honest policy and an attack policy under one protocol, in one eval log
Running Evals on Hawk	Submit evals to a shared Hawk cluster and view results
EC2 Fleet	Run evaluations on a fleet of EC2 workers
Simulated Sandbox	The no-Docker simulated sandbox backend

Protocols and Monitors

Page	Description
Protocols and Policies	How the red team's policy and the blue team's protocol are built and wired into an eval
Monitoring Trajectories	Score trajectories with action and trajectory monitors
Function Registry	Registering policies and protocols

Analysis

Page	Description
Trajectories	Understand trajectory files, IDs, conversion, upload, and download
Safety Curves	Usefulness, safety, audit budget and cost of a control eval

Building Environments

Page	Description
Development Setup	Get your local environment running
Live Development	Iterate on envs and tasks with `ct live`
Making Environments	Create evaluation environments
Environment Architecture	Settings, env discovery, and repo layout
Porting Settings	Bring an existing benchmark in as a setting
Internet Simulator	Simulated external services inside environments
Hawk Values Contract	The hand-authored `hawk-values.yaml` each env needs to run on Hawk
Adding a Dataset	Import an external monitoring dataset from Hugging Face or GitHub

Tasks and Scorers

Page	Description
Making Main Tasks	Define tasks for agents
Making Side Tasks	Design sabotage objectives
Side Task Failure Types	Classify side tasks as live or delayed
Making Scorers	Write task validators
Side-Task Scorer Patterns	Reusable `scorer_utils` helpers for side-task scorers
Auditing Environments	Environment quality audits via `ct extras` subcommands
Task Generation and Audit Commands	The `ct extras` commands that generate tasks and audit environments, tasks, and trajectories

Sabotage Trajectories

Page	Description
Making Sabotage Trajectories	Hand-craft sabotage trajectories (strajs) that accomplish a side task while evading the monitor
Sabotage Trajectory Review	The `@straj-review` bot for sabotage trajectory (straj) pull requests

Reference

Command Line, Python, and HTTP

Page	Description
CLI Reference	Generated reference for every Control Tower command and option.
Python Reference	Generated reference for the registries Control Tower is extended through.
HTTP API	Viewer routes, wire conventions, auth, and self-hosting

Data and Glossary

Page	Description
Database	MongoDB collections and access
Glossary	Abbreviations and project terms used across the documentation

Project Structure

Directory	Purpose
`src/control_tower/environments/`	Environment infrastructure (settings, the env registry, env processes, the internet simulator)
`packages/ct-setting-sdk/`	The setting SDK setting packages build on (tasks, scorer utils, the env process server)
`.settings/`	Cloned environment repos (gitignored, populated via `ct settings pull`)
`src/control_tower/trajectories/`	Trajectory format handling
`src/control_tower/viewer/`	Client for the viewer's HTTP API (`packages/viewer/` is the viewer app)
`src/control_tower/extras/`	Tooling behind `ct extras`
`src/control_tower/eval/`	The eval engine and the `ct run eval` and `ct run monitor` runners
`src/control_tower/protocols/`	The built-in blue-team protocols
`src/control_tower/policies/`	The built-in red-team policies
`src/control_tower/metrics/`	The `audit` scorer and the usefulness, safety, audit budget and cost metrics
`docs/`	This documentation
`tests/`	Test suite
`apps/docs/`	Docs and environment reference site