Skip to main content
Back to challenges
Challenge

Automated Corporate Account Verification Engine with Mastra AI

Opening corporate bank accounts in Singapore requires parsing multi-party ownership and ACRA registry disclosures. Build a TypeScript verification workflow using Mastra AI to process corporate filings and check identity requirements automatically.

Workflow AutomationHosted 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 automated corporate KYC and account onboarding workflow using Mastra AI TypeScript agent framework.

Delivery guide

How work is evaluated

Evaluation

Evaluates accuracy of UBO extraction and verification status logic.

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

ubo_extracted

Ensures individual UBO is properly identified

Binary check

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

Dimension 2

verification_accuracy

Accuracy of onboarding recommendation decision • 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

  • Use Mastra AI agent framework in TypeScript to orchestrate workflows

  • Extract Ultimate Beneficial Ownership (UBO) structures from corporate documents

  • Verify compliance against MAS corporate account opening guidelines

Resources and assets

Reference links and supporting material

Dataset notes

Synthetic ACRA corporate registry structures and owner identities.

Challenge setup

Evaluates accuracy of UBO extraction and verification status logic.

Challenge input

JSON corporate ownership tree

Mastra AI

TypeScript-native workflow and memory orchestration

Evaluated output

JSON listing identified_ubos and approval_recommendation

Evaluation checks
  • Ensures individual UBO is properly identified
  • Accuracy of onboarding recommendation decision • target: 1 • range: 0-1
Configured evaluation evidence
  • Benchmark: KYC-Bench
  • Verification 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
  • Larridin · Optional
  • Guidance · Optional
Orchestration
  • Mastra AI · Required

Evaluation contract

  • ubo_extracted · Weight 1
  • verification_accuracy · Weight 1

Metrics

  • verification_accuracy · Target 1

Benchmarks

  • KYC-Bench
  • security

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON corporate ownership tree

    Output: JSON listing identified_ubos and approval_recommendation

    Execution harness: JavaScript

Evaluation tools

  • Mastra AI · Agent Framework

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Automated Corporate Account Verification Engine with Mastra AI