The way actual users experience your system is essential to assessing the true impact of its predictions, recommendations, and decisions.

• Design features with appropriate disclosures built-in: clarity and control are crucial to a good user experience.
• Consider augmentation and ...

The use of several metrics rather than a single one will help you to understand the tradeoffs between different kinds of errors and experiences.

Consider metrics including feedback from user surveys, quantities that track overall system performance and short- and long-term product health (e...

• Conduct rigorous unit tests to test each component of the system in isolation.
• Conduct integration tests to understand how individual ML components interact with other parts of the overall system.
• Proactively detect input drift by testing the statistics of the inputs to th...

• Issues will occur: any model of the world is imperfect almost by definition. Build time into your product roadmap to allow you to address issues.
• Consider both short- and long-term solutions to issues. A simple fix (e.g., blocklisting) may help to solve a problem quickly, but may not...

The difference between performance during training and performance during serving—is a persistent challenge.

During training, try to identify potential skews and work to address them, including by adjusting your training data or objective function. During the evaluation, continue to try t...

• A model trained to detect correlations should not be used to make causal inferences, or imply that it can. 
• Machine learning models today are largely a reflection of the patterns of their training data.
• Communicate limitations to users where possible.

Reliable, effective user-centered AI systems should be designed following general best practices for software systems, together with practices that address considerations unique to machine learning.