Back to challenges
Challenge

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
Challenge brief

What you are building

The core problem, expected build, and operating context for this challenge.

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

Delivery guide

How work is evaluated

Evaluation

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

Datasets

Shared data for this challenge

Review public datasets and any private uploads tied to your build.

Evaluation rubric

How submissions are scored

These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.

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

What you should walk away with

  • 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 and assets

Reference links and supporting material

Dataset notes

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

How this agent runs

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

Checks for
  • 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
Proof of success
  • Benchmark: Merchant Risk & Identity Auditing Benchmark
  • Onboarding Audit Accuracy target: 0.95
  • 1 public reference case
Runtime evidence
  • Python execution harness
  • Python sandbox (unavailable on Versalist)
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

Recipe state

This is a preview. The configuration can change before the evaluation recipe is locked.

Frequently Asked Questions about Merchant Onboarding Verification System with AutoGen