Catalogue of Tools & Metrics for Trustworthy AI

These tools and metrics are designed to help AI actors develop and use trustworthy AI systems and applications that respect human rights and are fair, transparent, explainable, robust, secure and safe.

AiEnsured



AiEnsured is a commercial testing platform for AI products, designed to support the deployment of responsible AI. AI systems can fail in ways that conventional software testing does not catch, such as biased outcomes, unexpected behaviour on unusual inputs, vulnerability to attacks and declining performance over time. AiEnsured brings together testing methods for these risks in a single suite, covering a model's development, testing and operation. It is developed in India and has been recognised in Forbes India's DGEMS 200 list.

The platform offers several types of testing. Fairness and bias evaluation checks whether models treat groups of people differently. Explainability and interpretability features help users understand how models reach their decisions. Security and adversarial robustness testing checks whether models can be misled by deliberately manipulated inputs. Other methods generate test cases automatically. These include corner case generation, which explores rare and extreme inputs; test generation based on linguistic analysis; and metamorphic testing, which checks whether outputs change consistently when inputs are changed in known ways. The platform also checks models for privacy and GDPR compliance.

Further features support the wider machine learning lifecycle. These include data augmentation, automated model generation, experiment management, model comparison through A/B testing, and performance and inference testing. Once models are deployed, monitoring features detect concept drift, which occurs when changes in real-world data reduce a model's accuracy.

Use Cases

There is no use cases for this tool yet.

Would you like to submit a use case for this tool?

If you have used this tool, we would love to know more about your experience.

Add use case
Partnership on AI

Disclaimer: The tools and metrics featured herein are solely those of the originating authors and are not vetted or endorsed by the OECD or its member countries. The Organisation cannot be held responsible for possible issues resulting from the posting of links to third parties' tools and metrics on this catalogue. More on the methodology can be found at https://oecd.ai/catalogue/faq.