Back to evaluations
Public evaluation
ondc_catalog_guardrail_eval
Evaluates catalog item processing for safety policy compliance and output schema alignment.
Evaluation type
task based
Challenge
ONDC Merchant Catalog Guardrailing with CrewAI and NVIDIA NeMo
Difficulty
Intermediate
Rigor
Unspecified
Evaluation overview
How the linked challenge is judged: tasks, benchmarks, and criteria count.
Tasks
1
Benchmarks
0
Criteria
0
Task templates
Inputs and expected outputs.
Task 1
ondc_catalog_guardrail_eval
Processes raw merchant product entries, applies NeMo guardrails, and emits sanitized ONDC JSON.
Input format
JSON containing raw_title, description, price, and category_claim.
Output format
JSON containing ondc_title, normalized_category, safety_passed (bool), and flag_reasons list.