Skip to main content
Back to challenges
Challenge

Build a Hedge Fund Compliance and Capital Allocation Pipeline with AutoGen

Design an automated regulatory reporting and risk management agent system for Singapore hedge fund managers. Using AutoGen multi-agent collaboration, separate agents will monitor MAS risk compliance, anchor decision logic, and draft investor risk disclaimers 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 framework to audit hedge fund portfolio leverage and generate MAS regulatory compliance filings.

Delivery guide

How work is evaluated

Evaluation

Evaluate multi-agent consensus on fund leverage compliance and MAS disclosure generation.

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

compliance_flag_test

Correctly flags leverage > 3.0x as non-compliant

Binary check

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

Dimension 2

report_completeness

Inclusion of all required MAS risk disclosure sections • target: 0.95 • 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

  • Configure AutoGen multi-agent conversation topologies for compliance verification

  • Automate portfolio value-at-risk (VaR) calculations against MAS exposure limits

  • Build dynamic policy check functions for fund manager key-person risk tracking

  • Produce validated MAS SFA compliance reports with full audit traces

Resources and assets

Reference links and supporting material

Dataset notes

Anonymized fund balance sheet records and portfolio asset allocation snapshots.

Challenge setup

Evaluate multi-agent consensus on fund leverage compliance and MAS disclosure generation.

Challenge input

JSON containing total_assets, gross_exposure, fund_name

AutoGen

Microsoft agent framework for multi-persona financial review.

Evaluated output

JSON containing leverage_ratio, mas_compliant (bool), remediation_required

Evaluation checks
  • Correctly flags leverage > 3.0x as non-compliant
  • Inclusion of all required MAS risk disclosure sections • target: 0.95 • range: 0-1
Configured evaluation evidence
  • Benchmark: FinTech_RegCompliance_Bench
  • Report Completeness target: 0.95
  • 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
  • Aim · Optional
  • LatticeFlow AI · Optional

Evaluation contract

  • compliance_flag_test · Weight 1
  • report_completeness · Weight 1

Metrics

  • report_completeness · Target 0.95

Benchmarks

  • FinTech_RegCompliance_Bench
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON containing total_assets, gross_exposure, fund_name

    Output: JSON containing leverage_ratio, mas_compliant (bool), remediation_required

    Execution harness: Python

Evaluation tools

  • AutoGen · Multi-Agent Framework

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Build a Hedge Fund Compliance and Capital Allocation Pipeline with AutoGen