Skip to main content
Back to challenges
Challenge

Build a Multi-Rail Merchant Fee Optimization Crew with CrewAI

Shifting debit fee regulations drive merchants to evaluate alternative routing options across regional debit networks. Build a multi-agent collaborative crew using CrewAI where specialized agents analyze fee schedules, route transactions, and audit settlement math.

CybersecurityHosted 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 a team of specialized CrewAI agents (Fee Analyst, Routing Agent, Auditor) to optimize debit card network selection.

Delivery guide

How work is evaluated

Evaluation

Evaluates cost savings and routing choice accuracy produced by the agent crew.

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

test_least_cost_selection

Verify cheapest network selected for non-exempt ticket

Binary check

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

Dimension 2

optimization_accuracy

Percentage of transactions routed to true minimum fee network • target: 0.98 • range: 0.9-1

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 role-playing agents in CrewAI (Fee Auditor, Route Optimizer, Compliance Verifier).

  • Orchestrate hierarchical or sequential task delegation across agents.

  • Deliver automated debit processing routing maps with verified margin optimization.

Resources and assets

Reference links and supporting material

Dataset notes

Synthetic debit transaction batches with interchange rate structures.

Challenge setup

Evaluates cost savings and routing choice accuracy produced by the agent crew.

Challenge input

JSON transaction batch profile with ticket sizes and network options

CrewAI

Framework requirement

Evaluated output

JSON with recommended_network, total_fee, projected_savings

Evaluation checks
  • Verify cheapest network selected for non-exempt ticket
  • Percentage of transactions routed to true minimum fee network • target: 0.98 • range: 0.9-1
Configured evaluation evidence
  • Benchmark: Merchant Optimization Benchmark v1
  • Optimization 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
  • CrewAI · Required
  • crewAI · Optional

Evaluation contract

  • test_least_cost_selection · Weight 1
  • optimization_accuracy · Weight 1

Metrics

  • optimization_accuracy · Target 0.98

Benchmarks

  • Merchant Optimization Benchmark v1
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON transaction batch profile with ticket sizes and network options

    Output: JSON with recommended_network, total_fee, projected_savings

    Execution harness: Python

Evaluation tools

  • CrewAI · agent_framework

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Build a Multi-Rail Merchant Fee Optimization Crew with CrewAI