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.
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.
How work is evaluated
Tests multi-agent conversation convergence and compliance violation detection rate.
Shared data for this challenge
Review public datasets and any private uploads tied to your build.
How submissions are scored
These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.
flags_misleading_claims
Detects misleading statements
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
violation_detection_recall
Recall metric for regulatory breach identification • target: 0.95 • range: 0-1
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
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
Reference links and supporting material
Synthetic financial advisor interaction logs containing compliant and non-compliant scenarios.
How this agent runs
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
- Detects misleading statements
- Recall metric for regulatory breach identification • target: 0.95 • range: 0-1
- Benchmark: FinReg-Bench
- Violation Detection Recall target: 0.95
- 1 public reference case
- Python execution harness
- Python sandbox (unavailable on Versalist)
View technical recipe
Configured tools
- AutoGen · Required
- Coplay AI · Optional
- Vijil · Optional
Evaluation contract
- flags_misleading_claims · Weight 1
- violation_detection_recall · Weight 1
Recipe state
This is a preview. The configuration can change before the evaluation recipe is locked.