Skip to main content
Back to challenges
Challenge

Agentic AI Supervisory Compliance System with AutoGen & Coplay AI

Regulators and financial institutions require multi-agent oversight to verify AI advisory suggestions against regulatory norms. Construct a multi-agent compliance review team using AutoGen and Coplay AI to audit financial advisory outputs and enforce MAS regulatory boundaries.

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.

Design a multi-agent regulatory compliance auditor using AutoGen multi-agent orchestration and Coplay AI assistant interfaces.

Delivery guide

How work is evaluated

Evaluation

Tests multi-agent conversation convergence and compliance violation detection rate.

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

flags_misleading_claims

Detects misleading statements

Binary check

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

Dimension 2

violation_detection_recall

Recall metric for regulatory breach identification • 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

  • Orchestrate multi-agent dialogue loops with AutoGen

  • Implement regulatory rule validation tools within Coplay AI interfaces

  • Generate automated compliance audit reports for financial AI systems

Resources and assets

Reference links and supporting material

Dataset notes

Synthetic financial advisor interaction logs containing compliant and non-compliant scenarios.

Challenge setup

Tests multi-agent conversation convergence and compliance violation detection rate.

Challenge input

JSON text of AI customer advice transcript

AutoGen

Agent collaboration and validation

Coplay AI

User interface workflow orchestration

Evaluated output

JSON report containing compliance_status, violations, and recommended_edits

Evaluation checks
  • Detects misleading statements
  • Recall metric for regulatory breach identification • target: 0.95 • range: 0-1
Configured evaluation evidence
  • Benchmark: FinReg-Bench
  • Violation Detection Recall 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
  • Coplay AI · Optional
  • Vijil · Optional

Evaluation contract

  • flags_misleading_claims · Weight 1
  • violation_detection_recall · Weight 1

Metrics

  • violation_detection_recall · Target 0.95

Benchmarks

  • FinReg-Bench
  • security

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON text of AI customer advice transcript

    Output: JSON report containing compliance_status, violations, and recommended_edits

    Execution harness: Python

Evaluation tools

  • AutoGen · Multi-Agent Framework
  • Coplay AI · Assistants & Interfaces

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Agentic AI Supervisory Compliance System with AutoGen & Coplay AI