eval-driven ai development6 / 9
assertions on ai output, not vibes
Claude wrote a yes/no classifier eval. The actual answer is "YES"
but the eval expects "yes" and fails. The fix is to make the
comparison case-insensitive. Change line 4 so the script prints
pass.
Expected output:
pass
The break is on line 4 — but read the whole snippet first.
⌘↵ runs the editor.
Booting Python…
Output
[promptdojo:~]$ _