Skip to main content
Loading navigation
Back to challenges

Build Luxury E-Commerce Verification Crew with CrewAI

Luxury fashion platforms operating on ONDC require automated verification to prevent counterfeit listings and price discrepancies. Build a multi-agent crew using CrewAI with specialized inspector roles to analyze product listings and flag compliance errors with over 95% precision.

Business OperationsHosted by Vera
Sign in free to start

What you are building

Orchestrate collaborative role-based CrewAI agents for luxury apparel authentication and compliance on open digital networks.

How work is evaluated

Evaluation

Evaluates multi-agent catalog audit accuracy against gold luxury brand verification datasets.

Datasets

Public datasets, plus the private datasets you have access to.

How submissions are scored

Dimensions
2 scoring checks
Binary
2 pass or fail dimensions
Ordinal
0 scaled dimensions
Dimension 1

flagged_reasons_non_empty

Ensures flagged listings contain specific cause tags

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Dimension 2

audit_precision

Precision score of counterfeit and listing fraud identification • target: 0.95 • range: 0-1

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Learning goals

  • Orchestrate collaborative agents with specific roles using CrewAI

  • Build brand verification and catalog compliance evaluation tools

  • Flag pricing discrepancies and unauthorized luxury resellers on digital catalog feeds

Resources

Dataset notes

Curated dataset of e-commerce luxury fashion listings and reseller price points.

Challenge setup

Evaluates multi-agent catalog audit accuracy against gold luxury brand verification datasets.

Challenge input

JSON containing product_title, seller_name, price_inr, MSRP_inr, image_url

CrewAI

Allows creation of autonomous multi-agent inspection teams

Evaluated output

JSON containing authenticity_status, risk_score, and flagged_reasons

Evaluation checks
  • Ensures flagged listings contain specific cause tags
  • Precision score of counterfeit and listing fraud identification • target: 0.95 • range: 0-1
Configured evaluation evidence
  • Benchmark: Luxury-Audit-Bench
  • Audit Precision target: 0.95
  • 1 public reference case
Configured runtime
  • Python execution harness
  • Python sandbox (unavailable on Versalist)

Shows the first task, up to three tools, and up to three evidence items.

View technical recipe

Configured tools

Action Space
  • CrewAI · Required
  • crewAI · Optional
  • Zed · Optional

Evaluation contract

  • flagged_reasons_non_empty · Weight 1
  • audit_precision · Weight 1

Metrics

  • audit_precision · Target 0.95

Benchmarks

  • Luxury-Audit-Bench
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON containing product_title, seller_name, price_inr, MSRP_inr, image_url

    Output: JSON containing authenticity_status, risk_score, and flagged_reasons

    Execution harness: Python

Evaluation tools

  • CrewAI · Agent Orchestration

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Build Luxury E-Commerce Verification Crew with CrewAI