← Browse tools

Observability & evaluation

Inspect AI

Composable evaluation tasks that can include tool use and multi-turn interactions, with inspectable execution records.

Overview

Research summary

Inspect AI is an evaluation framework created by the UK AI Security Institute. Developers compose evaluations from datasets, model interactions, tools, and scoring logic, including multi-turn dialogue and model-graded assessment. The framework supports extensions supplied through Python packages and includes a collection of ready-to-run evaluations. Its command-line and browser inspection workflows support reviewing the evidence behind an evaluation result. Inspect is useful when an assessment needs to represent an interactive agent task rather than only compare a single completion with a reference answer.

Repository summary

Stars
Unavailable
Open issues
Unavailable
Last push
Unavailable
Commits, 90 days
Unavailable
Repository activity
Not scored
Version
Unavailable

Recorded catalogue figures. View repository data and provenance →

Classification

Pricing & services

Paid services unknown

Whether the provider offers paid products or services has not been established.

Licence scope

Implementation

Recorded implementation details and interfaces for Inspect AI.

Implementation details

Python evaluation framework with CLI and TypeScript result viewer

Languages
Python
Repository type
source

Recorded interfaces and capabilities

Licence scope

Repository

Repository snapshots, release information and recorded maintenance signals.

Repository snapshot

UKGovernmentBEIS/inspect_ai ↗

Stars
Unavailable
Open issues
Unavailable
Last push
Unavailable
Commits, 90 days
Unavailable
Repository activity
Not scored
Archived
Not recorded

Repository activity is a snapshot, not a quality or popularity ranking. It combines recent-push freshness (50%), 90-day commits (30%) and issue pressure (20%).

Maintenance and provenance

Catalogue snapshot
2026-10-06

Documentation

Recorded references and research provenance for this entry.

Recorded sources 4

Research metadata

Research date
2026-10-02
Catalogue snapshot
2026-10-06