eval-driven ai development9 / 9
assertions on ai output, not vibes
Checkpoint
One last thing before we move on. Same surface as a write step — but the lesson doesn't complete until this passes.
Last one. The starter has a regression_cases list and a stub
classifier that has a known bug — it returns "no" for the input
"cancel my account", which should be "yes". Add the missing case
to regression_cases so it would catch this exact bug. Run the suite
and confirm the output is 2/3 (two pass, one — the new regression
case — fails).
Add one entry: input "cancel my account", expected "yes", name
"account_cancel".
Expected output:
2/3
⌘↵ runs the editor.
Booting Python…
Output
[promptdojo:~]$ _