Skip to main content
Back to challenges
Challenge

Refinery & Cross-Border Pipeline Scheduling Engine with AutoGen

Crude oil distribution between regional refineries in Iraq and export pipelines requires coordinated scheduling between independent pipeline operators and refining teams. Construct a multi-agent pipeline scheduling engine using Microsoft AutoGen. The system coordinates the Pipeline Dispatch Agent, Refinery Intake Agent, and Export Terminal Agent to establish a 90-day pumping schedule that avoids pipeline pressure bottlenecks and terminal storage overflow.

Business OperationsHosted 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 pipeline flow and refinery intake schedules across autonomous agents using AutoGen.

Delivery guide

How work is evaluated

Evaluation

Evaluates 90-day pipeline flow schedule feasibility and constraint adherence.

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

schedule_valid_true

Ensure generated schedule violates zero hard limits.

Binary check

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

Dimension 2

capacity_utilization_efficiency

Optimal utilization percentage achieved without overflow. • target: 0.85 • 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

  • Configure AutoGen multi-agent workflows for multi-node pipeline scheduling.

  • Implement linear programming tools inside agent tool suites.

  • Resolve storage tank capacity constraints across 90-day horizon.

Resources and assets

Reference links and supporting material

Dataset notes

90-day synthetic telemetry and capacity constraints for crude export pipelines.

Challenge setup

Evaluates 90-day pipeline flow schedule feasibility and constraint adherence.

Challenge input

JSON with tank_capacities, pipeline_limits, daily_refinery_intake

AutoGen

Framework for multi-actor collaborative optimization.

Evaluated output

JSON with schedule_valid, max_storage_utilized_pct, bottleneck_detected

Evaluation checks
  • Ensure generated schedule violates zero hard limits.
  • Optimal utilization percentage achieved without overflow. • target: 0.85 • range: 0-1
Configured evaluation evidence
  • Benchmark: AutoGen-Ops-Bench
  • Capacity Utilization Efficiency target: 0.85
  • 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
  • Sarvam AI · Optional

Evaluation contract

  • schedule_valid_true · Weight 1
  • capacity_utilization_efficiency · Weight 1

Metrics

  • capacity_utilization_efficiency · Target 0.85

Benchmarks

  • AutoGen-Ops-Bench
  • energy

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON with tank_capacities, pipeline_limits, daily_refinery_intake

    Output: JSON with schedule_valid, max_storage_utilized_pct, bottleneck_detected

    Execution harness: Python

Evaluation tools

  • AutoGen · Multi-Agent System

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Refinery & Cross-Border Pipeline Scheduling Engine with AutoGen