AI Assessment Sandbox Configurator


An open-source tool to streamline the creation of AI testing sandboxes customized for each use case and vertical

Catalogue of AI Tests & Controls

An open-source European asset

Access the catalogue

GitHub Repository

To get and contribute to the source code

Access GitHub

Setting up a technical environment to assess AI can be complex and time consuming. Teams need to find relevant tests, set up sandbox environments, choose the right metrics, and bring results together into clear insights. This requires collaboration across technical, legal, and business teams.   

The AI Assessment Sandbox Configurator, is an open source tool that helps organisations efficiently and rapidly configure and deploy AI assessment sandboxes tailored to their specific use cases. It  allows organizations to significantly reduce the time and cost to create, deploy, and use AI Assessment Sandboxes. 

ai sandbox


The Catalogue of AI tests & controls

The “Hugging Face for AI Assessment”: an open-source European asset co-developed by a broad community. A structured, extensible catalogue of AI testing tools, controls and datasets, integrated through an open plug-in API interface, possibly endorsed by National Competent Authorities, with potential to evolve into vertical marketplaces.
Discover the Catalogue of AI Tests & Controls
ai sandbox


Configure your AI Assessment Sandbox

By selecting AI tests, controls and datasets from the catalogue, that are relevant to your use case you can generate a customized sandbox with a dedicated collaborative dashboard and a report generator with templates fitting your specific needs.

Benefits of the AI Assessment Sandbox Configurator

Adapt to any AI use case

Every AI use case has different needs. The configurator helps you map your specific context and requirements to the right tests, metrics and controls.

Bring all results together and make them easy to compare

All test results and control checks flow into one dashboard and report. Outputs are aligned automatically, so you can compare and assess them easily. All is recorded in temper-proof logs for auditability.

Align teams with a shared understanding

A common assessment structure helps multidisciplinary teams understand results in the same way. It also makes it easier to collaborate and have clear discussions with stakeholders.

Ready to contribute to the project?

The AI Assessment Sandbox Configurator is an open source tool built with and for its community. You are welcome to use it, adapt it, and contribute to its evolution.   

You can contribute in various ways:

  • Install it in your own environment and use it to generate tailored AI assessment sandboxes for your use case and needs. Then share with us your experience and feedback for improvement.
  • Extend the catalogue of AI tests and controls by integrating your AI tests and controls using the plug-in interface.
  • Contribute to the code of the configurator

This open and collaborative approach helps build trust and supports digital sovereignty through transparency and openness. Join its development!

Technical documentation

Step-by-step documentation from GitHub, including how to download, install and run the AI Assessment Sandbox Configurator
Access now!

Co-developed by

LIST uni.lu