Challenge

Claude Agents SDK & Sourcegraph Amp Luxury Merchant Verification

Premium e-commerce platforms struggle with digital public infrastructure fraud and counter-fake verification on open networks. You will develop an autonomous inspection agent that cross-references brand registries, tax filings, and product authenticity documentation to automate luxury merchant trust scoring.

Business OperationsHosted by Vera
Challenge brief

What you are building

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

Construct a Claude Agents SDK workflow integrated with Sourcegraph Amp repository inspection tools to dynamically audit merchant compliance and product authenticity metrics.

Delivery guide

How work is evaluated

Evaluation

Evaluates seller authenticity audit precision across simulated business registries.

Datasets

Shared data for this challenge

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

Loading datasets...
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

Invalid GSTIN Rejection

Must reject sellers with invalid or unverified GSTIN formats

Binary check

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

Dimension 2

Verification Precision

Accuracy in detecting fraudulent trademark claims • target: 0.96 • range: 0.88-1

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

  • Build custom tool calls in Claude Agents SDK for GSTIN and trademark registry auditing

  • Integrate Sourcegraph Amp workspace automation to inspect code repositories and API integration points

  • Construct a dynamic risk scoring engine for seller onboarding on open e-commerce rails

  • Enforce compliance checks for high-value fashion and luxury catalog listings

Resources and assets

Reference links and supporting material

Dataset notes

Synthetic merchant filings containing GSTIN numbers, brand trademark registry entries, and catalog listings.

How this agent runs

Evaluates seller authenticity audit precision across simulated business registries.

Challenge input

JSON with seller business name, GSTIN, trademark registration number, and repo URL

Claude Agents SDK

Provides reasoning and structured tool interaction.

Sourcegraph Amp

Inspects merchant integration codebase for security compliance.

Evaluated output

JSON with trust_score (0-100), verification_status, and risk_flags array

Checks for
  • Must reject sellers with invalid or unverified GSTIN formats
  • Accuracy in detecting fraudulent trademark claims • target: 0.96 • range: 0.88-1
Proof of success
  • Benchmark: MerchantRisk-Bench
  • Verification Precision target: 0.96
  • 1 public reference case
Runtime evidence
  • Python execution harness
  • Python sandbox (unavailable on Versalist)
View technical recipe

Configured tools

Action Space
  • Sourcegraph Amp · Required
  • Libretto · Optional
  • Retell AI · Optional
Observation
  • Sourcegraph Amp · Required

Evaluation contract

  • Invalid GSTIN Rejection · Weight 1
  • Verification Precision · Weight 1

Recipe state

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

Frequently Asked Questions about Claude Agents SDK & Sourcegraph Amp Luxury Merchant Verification