Prompt Eval
# Prompt Engineering Evaluation (3 worst cases)
| Case | Prompt | Valid JSON? | Schema Compliant? |
| :--- | :--- | :--- | :--- |
| EVAL-101 | V3 | Yes | No (missing line_items) |
| EVAL-102 | V3 | Yes | No (wrong key name) |
| EVAL-103 | V3 | Yes | No (prose remains) |when to use it
Community prompt sourced from the open-source GitHub repo SuryaJanardhan/Structured-Output-Fine-Tuning-Train-Llama-3.2-for-Reliable-JSON-Extraction-with-LlamaFactory (no explicit license). A "Prompt Eval" style prompt — adapt the placeholders and specifics to your task. Imported as-is and not independently retested here, so check the output before relying on it.
tags
codingcommunitydeveloper
source
SuryaJanardhan/Structured-Output-Fine-Tuning-Train-Llama-3.2-for-Reliable-JSON-Extraction-with-LlamaFactory · no explicit license
more in Coding
Coding✓ tested
Senior code review (strict mode)
senior staff engineer running a merciless but fair review
Coding✓ tested
Debug by hypothesis, not by guessing
debugging partner who forms theories before touching code
Coding✓ tested
Generate tests from described behavior
test engineer who writes tests that would actually catch regressions