Skip to main content
Loading navigation
Back to challenges

Merchant Onboarding Verification System with AutoGen

Premium e-commerce merchants suffer from identity spoofing and fraudulent chargebacks during high-volume digital onboarding. Build an autonomous multi-agent merchant audit workflow using AutoGen to inspect GSTIN credentials and lower fraud onboarding risk by 85%.

Business OperationsHosted by Vera
Sign in free to start

What you are building

Construct an autonomous multi-agent high-value merchant onboarding audit system using Microsoft AutoGen with Human-in-the-Loop review.

How work is evaluated

Evaluation

Evaluates merchant verification accuracy, synthetic identity fraud flagging, and human escalation precision.

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

verify_escalation_logic

Ensures mismatched PAN/GSTIN entities are forced to HITL review

Binary check

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

Dimension 2

onboarding_audit_accuracy

Precision of risk tier assignments compared to compliance audit baseline • 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

  • Design conversational multi-agent systems using Microsoft AutoGen

  • Implement Human-in-the-Loop (HITL) approval nodes for high-risk merchant applications

  • Verify GSTIN, PAN, and MCA corporate filing records via API tools

  • Detect luxury retail brand counterfeiting and synthetic identity spoofing

Resources

Dataset notes

Dataset of luxury merchant onboarding applications, GSTIN filings, MCA company registration logs, and brand infringement reports.

Challenge setup

Evaluates merchant verification accuracy, synthetic identity fraud flagging, and human escalation precision.

Challenge input

JSON with gstin, pan, brand_name, and bank_account_name

AutoGen

Microsoft's framework for building multi-agent conversational systems.

Evaluated output

JSON containing onboarding_decision, risk_tier, and hitl_escalation_required

Evaluation checks
  • Ensures mismatched PAN/GSTIN entities are forced to HITL review
  • Precision of risk tier assignments compared to compliance audit baseline • target: 0.95 • range: 0-1
Configured evaluation evidence
  • Benchmark: Merchant Risk & Identity Auditing Benchmark
  • Onboarding Audit Accuracy 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
  • AutoGen · Required
  • Fixie · Optional
Policy Serving
  • OpenRouter · Optional
Orchestration
  • OpenRouter · Optional

Evaluation contract

  • verify_escalation_logic · Weight 1
  • onboarding_audit_accuracy · Weight 1

Metrics

  • onboarding_audit_accuracy · Target 0.95

Benchmarks

  • Merchant Risk & Identity Auditing Benchmark
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON with gstin, pan, brand_name, and bank_account_name

    Output: JSON containing onboarding_decision, risk_tier, and hitl_escalation_required

    Execution harness: Python

Evaluation tools

  • AutoGen · Agent Orchestration Framework

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Merchant Onboarding Verification System with AutoGen