Skip to main content
Loading navigation
Back to challenges

Mastra AI Corporate Bank Onboarding Workflow Engine

Build a Mastra AI workflow pipeline to automate corporate bank account opening checks, verifying ACRA corporate entities and UBO disclosures. Reduce account setup latency from days to under 30 seconds with 98% document validation accuracy.

Workflow AutomationHosted by Vera
Sign in free to start

What you are building

Develop a TypeScript workflow network with Mastra AI to automate ACRA lookup and Ultimate Beneficial Owner (UBO) entity extraction.

How work is evaluated

Evaluation

Evaluates UBO extraction correctness and workflow duration for corporate onboarding pipelines.

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

UBO Extraction Correctness

Checks if all shareholders with >25% stake are identified as UBOs

Binary check

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

Dimension 2

validation_accuracy

Accuracy of entity verification checks • target: 0.98 • 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

  • Utilize Mastra AI graph workflows in TypeScript for deterministic AI step execution

  • Integrate ACRA (Accounting and Corporate Regulatory Authority) mock API tools

  • Automate Ultimate Beneficial Owner (UBO) shareholding tree parsing

  • Build real-time onboarding audit logs for corporate banking compliance teams

Resources

Dataset notes

Synthetic ACRA business profile records and UBO corporate structure trees.

Challenge setup

Evaluates UBO extraction correctness and workflow duration for corporate onboarding pipelines.

Challenge input

JSON containing company registration number (UEN) and profile payload

Mastra AI

TypeScript framework for constructing type-safe agent workflows

Evaluated output

JSON containing identified_ubos, status, and execution_duration_sec

Evaluation checks
  • Checks if all shareholders with >25% stake are identified as UBOs
  • Accuracy of entity verification checks • target: 0.98 • range: 0-1
Configured evaluation evidence
  • Benchmark: KYCBench
  • Validation Accuracy target: 0.98
  • 1 public reference case
Configured runtime
  • JavaScript execution harness
  • javascript 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
  • Mastra AI · Required
  • Agents.js · Optional
  • Arcee AI · Optional
Orchestration
  • Mastra AI · Required

Evaluation contract

  • UBO Extraction Correctness · Weight 1
  • validation_accuracy · Weight 1

Metrics

  • validation_accuracy · Target 0.98

Benchmarks

  • KYCBench
  • security

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON containing company registration number (UEN) and profile payload

    Output: JSON containing identified_ubos, status, and execution_duration_sec

    Execution harness: JavaScript

Evaluation tools

  • Mastra AI · Agent Framework

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Mastra AI Corporate Bank Onboarding Workflow Engine