Evaluation habits on the AI Learning track. Evaluate on the slice that matters: new users, rare classes, the latest month. An average can rise while the slice you care about falls.
This lesson assumes you already worked through Learning after launch.
The idea in practice
Report overall and two slices. Keep the slice definitions stable so weeks compare.
A concrete check
goal = {
'track': 'AI Learning',
'lesson': 'Evaluation habits',
}
checks = [
'input available at decision time',
'score matches the real decision',
'failure case written down',
]
print(goal['lesson'])
for item in checks:
print('-', item)
Run the sketch locally if you have Python. The printout is a reminder of the checks, not a trained model. Replace the strings with the real inputs from your own example before you treat it as a design.
What usually goes wrong
A single average that hides a broken region. When this happens, stop adding parameters or tools. Fix the check, the data, or the permission, then run the same example again.
What to write down
- The input you are allowed to use at decision time.
- The output and the score or pass rule.
- One failure you will test on purpose.
- What you will not claim the system can do.
Practice
Choose two slices for a model used in three cities.
Self-check
- Say Evaluation habits in one sentence that mentions an input and an output.
- Name the failure mode in this lesson and the check that would catch it.
Done when: you can explain this lesson without the page open, and you have a written failure case.