An AI model must not show internal system codes to a user. All user-facing text must describe the user's action or benefit. The purpose of the action is more important than the system's internal name for it.
By Pawan Nayar · from the LLOS AI Learning record
An AI model must not show internal system codes to a user.
All user-facing text must describe the user's action or benefit. The purpose of the action is more important than the system's internal name for it.
An AI model should never show internal codes like 'bandKey F/I/U/P' or 'section S1/S2'. It should not display format names like 'mcq_one_correct'. The AI model should also hide aspect names like 'regular_plural'. Every message a user sees must explain what the user will get or do. The message should not explain what the system calls the item or process. Focus on the user's experience and understanding.
An AI model shows a message: 'Loading F band…'. This message uses an internal system code. The user does not understand 'F band'. A better message would be: 'Opening Discover…'. This tells the user what is happening in a clear way.
Resolved from this lesson's own record — real definitions, not invented for this page.
More from the same record, pulled by shared topic — not written new for this page.
The word "band" can be confusing to users. It does not clearly explain what a section of content is.
An AI model must show full file paths after every major update. A major update is any change that modifies one or more files.
When an AI model's task fails, the AI model must stop. The AI model must explain what went wrong.
A curiosity-first headline can make the user want to learn more. For example, asking 'What stuck?' or 'What's stronger now?' can be more engaging than a simple summary.
An AI model must not show internal system codes to a user. All user-facing text must describe the user's action or benefit. The purpose of the action is more important than the system's internal name for it.