Skip to main content
Back to challenges
Challenge

Build a Cooperative Audit and Governance Engine with CrewAI

Develop a multi-agent cooperative auditing system tailored for ASEAN student and regional co-ops. Using CrewAI, assign specialized role-playing agents (Auditor, Bookkeeper, Compliance Officer) to review financial transaction ledgers and generate regulatory reports 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.

Orchestrate role-playing CrewAI agents to perform end-to-end audit compliance and fraud detection for student cooperative accounts.

Delivery guide

How work is evaluated

Evaluation

Evaluate accuracy of agent anomaly detection in cooperative transaction ledgers.

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

flagged_anomaly_correctness

All non-compliant transactions accurately flagged

Binary check

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

Dimension 2

audit_accuracy

Precision score of audit classification • 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

  • Define multi-agent roles, goals, and backstories using CrewAI Agent class

  • Build sequential and hierarchical crew task workflows for ledger parsing

  • Implement automated anomaly detection tools for expense reimbursement claims

  • Generate regulatory compliance scorecards formatted for cooperative registrar standards

Resources and assets

Reference links and supporting material

Dataset notes

Simulated cooperative financial ledger dataset featuring standard and anomalous entries.

Challenge setup

Evaluate accuracy of agent anomaly detection in cooperative transaction ledgers.

Challenge input

JSON containing list of transactions with fields id, amount, category, user

CrewAI

Framework for multi-agent role-playing workflows.

Evaluated output

JSON containing flagged_transactions, compliance_passed, summary

Evaluation checks
  • All non-compliant transactions accurately flagged
  • Precision score of audit classification • target: 0.95 • range: 0-1
Configured evaluation evidence
  • Benchmark: FinAudit_Crew_Bench
  • Audit Accuracy 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
  • CrewAI · Required
  • crewAI · Optional
  • Zed · Optional

Evaluation contract

  • flagged_anomaly_correctness · Weight 1
  • audit_accuracy · Weight 1

Metrics

  • audit_accuracy · Target 0.95

Benchmarks

  • FinAudit_Crew_Bench
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON containing list of transactions with fields id, amount, category, user

    Output: JSON containing flagged_transactions, compliance_passed, summary

    Execution harness: Python

Evaluation tools

  • CrewAI · Agent Framework

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Build a Cooperative Audit and Governance Engine with CrewAI