Several companies are actively engaged in the perception of the removal of bias in AI systems.

In February, Accenture released a toolkit that automatically detects bias in AI algorithms and helps data scientists mitigate that bias, and in May Microsoft launched a solution of its own. Now, Google is following suit.

Google debuted what it calls it’s What-If Tool, a “new bias-detecting feature of the TensorBoard web dashboard for its TensorFlow machine learning framework.” With only a model and a dataset, users are able to generate visualizations that explore the impact of algorithmic tweaks and adjustments, modulating the perceived bias in the model.