promptdojo_

Assertions on AI output, not vibes — step 7 of 9

Cursor wrote an eval that checks whether the model mentioned Paris somewhere in its answer. It used exact equality, which fails because the model returned a full sentence. Switch the check to a contains comparison so it passes.

Expected output:

pass
The break is on line 4 — but read the whole snippet first.

full-screen editor opens — close anytime to keep reading.