Skip to main content
Loading navigation
Back to challenges

Build an AutoGen Multi-Agent Dynamic Payment Routing Engine

Complex multi-rail payment ecosystems fail due to unoptimized gateway latency, failure rates, and interchange fees. Build a dynamic multi-agent system with AutoGen where negotiator, cost-optimizer, and compliance agents collaborate to route cross-border payments with 15% cost savings.

CybersecurityHosted by Vera
Sign in free to start

What you are building

Deploy an AutoGen multi-agent conversational loop to negotiate dynamic end-to-end payment routing under changing rail constraints.

How work is evaluated

Evaluation

Evaluates cost reduction percentage, route success rate, and multi-agent interaction efficiency.

Datasets

Public datasets, plus the private datasets you have access to.

How submissions are scored

Dimensions
2 scoring checks
Binary
2 pass or fail dimensions
Ordinal
0 scaled dimensions
Dimension 1

valid_rail_selection_test

Selected rail must fulfill specified latency SLA.

Binary check

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

Dimension 2

cost_saving_percentage

Percentage reduction in processing fees vs default route. • target: 0.15 • range: 0.05-0.3

Binary check

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

Learning goals

  • Build collaborative multi-agent conversations using Microsoft AutoGen

  • Implement Dynamic Group Chat patterns for payment gateway selection

  • Optimize end-to-end routing decisions across fee, latency, and SLA parameters

  • Incorporate human-in-the-loop intervention thresholds for high-value transactions

Resources

Dataset notes

Dataset of multi-rail payment scenarios with varying transaction volumes, fees, and latency constraints.

Challenge setup

Evaluates cost reduction percentage, route success rate, and multi-agent interaction efficiency.

Challenge input

JSON payment routing request detailing currency, speed priority, and max fee

AutoGen

Enables multi-agent conversational patterns and dynamic group collaboration.

Evaluated output

JSON containing selected rail, fee breakdown, and agent chat trace

Evaluation checks
  • Selected rail must fulfill specified latency SLA.
  • Percentage reduction in processing fees vs default route. • target: 0.15 • range: 0.05-0.3
Configured evaluation evidence
  • Benchmark: Multi-Agent Optimization Benchmark
  • Cost Saving Percentage target: 0.15
  • 1 public reference case
Configured runtime
  • Python execution harness
  • Python sandbox (unavailable on Versalist)

Shows the first task, up to three tools, and up to three evidence items.

View technical recipe

Configured tools

Action Space
  • AutoGen · Required
  • Microsoft AutoGen · Optional

Evaluation contract

  • valid_rail_selection_test · Weight 1
  • cost_saving_percentage · Weight 1

Metrics

  • cost_saving_percentage · Target 0.15

Benchmarks

  • Multi-Agent Optimization Benchmark
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON payment routing request detailing currency, speed priority, and max fee

    Output: JSON containing selected rail, fee breakdown, and agent chat trace

    Execution harness: Python

Evaluation tools

  • AutoGen · Multi-Agent Framework

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Build an AutoGen Multi-Agent Dynamic Payment Routing Engine