Giskard

We are the only collaborative & open-source solution to evaluate and test ML models.

We are data scientists & software engineers combining 20 years of experience in AI applications at Dataiku, Thales & Capgemini. We created Giskard because we were frustrated at how difficult it is to ensure ML models will perform correctly in production.

We are inspired by quality standards from mature industries: manufacturing, and software engineering. We want to bring AI into the age of quality.

2021-09-06

- Evaluate ML models collaboratively with business stakeholders
- Test ML models automatically using State-of-the-Art ML research
- Automate ML Testing in your CI/CD pipeline