Skip to main content
Back to challenges
Challenge

Automate Corporate Account Onboarding Workflows with AutoGen and Vercel AI SDK

Build a multi-agent onboarding assistant using AutoGen and Vercel AI SDK to automate corporate bank account verification in Singapore. Reduce verification delays while verifying ACRA filings and beneficial ownership 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.

Deploy an AutoGen multi-agent system supported by Vercel AI SDK components to orchestrate ACRA data validation and risk triage.

Delivery guide

How work is evaluated

Evaluation

Tests AutoGen agents on parsing ACRA profiles and executing verification workflows accurately.

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

match_status

Verifies correct classification of corporate application status

Binary check

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

Dimension 2

accuracy

Accuracy of UBO discrepancy detection • 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

What you should walk away with

  • Orchestrate collaborative AutoGen agents representing KYB Verification, Compliance, and Exception Handling

  • Integrate Vercel AI SDK UI state stream components for human-in-the-loop approvals

  • Validate Singapore ACRA business profile JSON schema structures automatically

  • Optimize processing time for non-complex corporate bank account opening applications

Resources and assets

Reference links and supporting material

Dataset notes

Synthetic dataset of 50 ACRA entity registration documents and applicant KYB forms.

Challenge setup

Tests AutoGen agents on parsing ACRA profiles and executing verification workflows accurately.

Challenge input

JSON containing applicant_details and acra_registry_data

AutoGen

Coordinates multi-agent interaction and verification rules.

Vercel AI SDK

Enables UI streaming and Human-in-the-loop interactions.

Evaluated output

JSON containing status (approved/escalated), confidence_score, and missing_docs

Evaluation checks
  • Verifies correct classification of corporate application status
  • Accuracy of UBO discrepancy detection • target: 0.98 • range: 0-1
Configured evaluation evidence
  • Benchmark: KYC Automation Test Suite
  • Accuracy target: 0.98
  • 1 public reference case
Configured runtime
  • Python execution harness
  • Python 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
  • AutoGen · Required
  • Vercel AI SDK · Optional
  • Aim · Optional
Orchestration
  • Vercel AI SDK · Optional

Evaluation contract

  • match_status · Weight 1
  • accuracy · Weight 1

Metrics

  • accuracy · Target 0.98

Benchmarks

  • KYC Automation Test Suite
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON containing applicant_details and acra_registry_data

    Output: JSON containing status (approved/escalated), confidence_score, and missing_docs

    Execution harness: Python

Evaluation tools

  • AutoGen · Multi-Agent Conversation Framework
  • Vercel AI SDK · Streaming & UI Agent SDK

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Automate Corporate Account Onboarding Workflows with AutoGen and Vercel AI SDK