An AI model should show progress with clear facts. Do not use general comparisons. Show numbers instead of rankings. Use facts instead of claims.
By Pawan Nayar · from the LLOS AI Learning record
An AI model should show progress with clear facts.
Do not use general comparisons. Show numbers instead of rankings. Use facts instead of claims.
An AI model should use specific, verifiable details. This helps the user feel their progress. Do not use general statements like 'you are doing better'. Show numbers and facts. For example, show 'you answered 10 questions correctly'. Do not say 'you are a top performer'. When a user sees clear evidence, they believe their progress is real. This makes the user feel good about their effort. The user feels they earned the progress.
A student uses an AI tutor. The AI says, 'You are now a top 10% learner.' The student does not feel this is real. The student does not know why. The AI changes its message. It says, 'You answered 95% of questions correctly this week. Last week, you answered 80% correctly.' The student sees the numbers. The student feels they earned the improvement.
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.
An AI model must have a plan for error messages. The plan should define different types of errors.
A system must have a clear signal for every failure. This signal can be a specific time, a tap pattern, or a wrong input.
A developer creates wrong answer choices for a question. Each wrong choice needs a matching explanation.
The AI model should give specific feedback. It should tell the user exactly what was done well or what needs work.
An AI model should show progress with clear facts. Do not use general comparisons. Show numbers instead of rankings. Use facts instead of claims.