Handle errors with care
AI models can often misunderstand user input, provide undesired results, or hallucinate information that was not given.
Make clear how well the system can do what it can do
Help the user understand how often the AI system may make mistakes. Users should understand that AI can be a reliable and helpful source, but also that its results should be scrutinized and verified.
Be accountable for errors
Understand the types of errors users might encounter and have a plan for resolving. Use the opportunity of an error to explain the underlying limitations which can build the mental model for the user and set the right expectations in the future.
Don’t humanise AI
An AI is not a human. If you don’t humanise AI and it makes a mistake, at least the emotional response is mitigated.