How AI describes Inspect

Inspect is an open-source framework for frontier AI evaluations developed by the UK AI Security Institute and Meridian Labs. It provides composable building blocks—datasets, agents, tools, and scorers—and ships with over 200 pre-built evaluations, plus web-based Inspect View and a VS Code extension for authoring and debugging. It supports flexible tool calling and multi-agent setups, works with many model providers and local inference options, and includes a sandboxing system to run untrusted model code in Docker, Kubernetes, Modal, Proxmox, Vagrant, and other environments.