Skip to main content
Back to challenges
Challenge

Build a Mastra AI Quick Commerce & D2C Merchant Risk Pipeline

Rapid onboarding of D2C sellers on quick commerce platforms increases exposure to operational vendor risk. Build a TypeScript workflow using Mastra AI to evaluate seller inventory health, fulfillment reliability, and return rates, producing automated merchant risk scores.

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.

Develop a Mastra AI TypeScript workflow with built-in state management and memory to compute merchant risk levels for quick commerce networks.

Delivery guide

How work is evaluated

Evaluation

Evaluates workflow completion and accuracy of merchant risk categorization.

Datasets

Challenge datasets

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

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

workflow_status_check

Verifies Mastra workflow completed execution

Binary check

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

Dimension 2

risk_tier_accuracy

Match score against risk model output • target: 1 • 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

  • Construct Mastra AI Agent workflows using TypeScript

  • Leverage Mastra memory and store drivers for historical seller metrics

  • Compute composite merchant risk scores based on operational metrics

  • Trigger automated credit limit adjustments based on seller risk profiles

Resources and assets

Reference links and supporting material

Dataset notes

Synthetic merchant fulfillment operational dataset containing return rates and quarterly GMV values.

Challenge setup

Evaluates workflow completion and accuracy of merchant risk categorization.

Challenge input

JSON payload of seller metrics

Mastra AI

TypeScript framework for workflow state management

Evaluated output

JSON object with risk_tier and max_credit_limit_inr

Evaluation checks
  • Verifies Mastra workflow completed execution
  • Match score against risk model output • target: 1 • range: 0-1
Configured evaluation evidence
  • Benchmark: E-Commerce Merchant Risk Benchmark
  • Risk Tier Accuracy target: 1
  • 1 public reference case
Configured runtime
  • JavaScript execution harness
  • javascript sandbox (unavailable on Versalist)

Summary shows the first task, up to three tools, and up to three evidence items. Open the technical recipe to view all configured items.

View technical recipe

Configured tools

Action Space
  • Mastra AI · Required
  • BoTorch · Optional
  • Fixie · Optional
Orchestration
  • Mastra AI · Required

Evaluation contract

  • workflow_status_check · Weight 1
  • risk_tier_accuracy · Weight 1

Metrics

  • risk_tier_accuracy · Target 1

Benchmarks

  • E-Commerce Merchant Risk Benchmark
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON payload of seller metrics

    Output: JSON object with risk_tier and max_credit_limit_inr

    Execution harness: JavaScript

Evaluation tools

  • Mastra AI · Agent Framework

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Build a Mastra AI Quick Commerce & D2C Merchant Risk Pipeline