Skip to main content
Back to challenges
Challenge

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
Challenge brief

What you are building

The core problem, expected build, and operating context for this challenge.

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

Delivery guide

How work is evaluated

Evaluation

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

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

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

What you should walk away with

  • 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 and assets

Reference links and supporting material

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)

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
  • 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