The four breakage classes — sort any LLM failure before you touch the prompt (step 7/9) · debugging broken ai output

promptdojo_›phase 04 · shipping discipline›ch 24 · debugging broken ai output

lesson 2 of 3 · the four breakage classes — sort any llm failure before you touch the promptstep 7 / 9

The model returned correct JSON: {"refund": "$48.20"}. A downstream "currency cleaner" regex was supposed to strip junk characters but instead strips the $ — turning $48.20 into 48.20. The user reads 48.20 and asks support what currency.

The model was right. The trace's raw_output is correct. The bug is in the regex on the post-processing line.

Fix the regex so it strips literal backticks (`) — which is what the cleaner was meant to do — and leaves the $ untouched.

Expected output:

raw:           {"refund": "$48.20"}
postprocessed: {"refund": "$48.20"}
class: parse (bug was in regex, not model)

The break is on line 8 — but read the whole snippet first.

⌘↵ runs the editor.read, then continue.

The model was right. The trace's raw_output is correct. The bug is in the regex on the post-processing line.

Fix the regex so it strips literal backticks (`) — which is what the cleaner was meant to do — and leaves the $ untouched.

Expected output:

raw:           {"refund": "$48.20"}
postprocessed: {"refund": "$48.20"}
class: parse (bug was in regex, not model)

The break is on line 8 — but read the whole snippet first.

this step needs the editor

on desktop today; in the app (coming soon). save your spot and we'll bring you back here when you're ready.

save my spot follow @TFisPython for the app launch

open this same url on a laptop to keep going today.

The four breakage classes — sort any LLM failure before you touch the prompt — step 7 of 9

this step needs the editor