Skip to main content
Back to challenges
Challenge

Emergency Refinery Repair Operations Crew with CrewAI

Urgent repairs at Kuwait's Al-Zour and Mina Al-Ahmadi refineries following regional disruptions require fast coordination of spare parts, specialized labor, and hot-work safety clearances. Build a CrewAI crew containing Procurement, Logistics, and Safety agents to automate repair workflow generation. Deliver approved repair work orders within 60 seconds.

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 specialized operational agents using CrewAI to construct emergency refinery repair sequences and material dispatch plans.

Delivery guide

How work is evaluated

Evaluation

Evaluates completeness and safety compliance of generated emergency refinery work orders.

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

safety_permit_included

Ensures hot work permit flag is enabled for high severity heat repair tasks

Binary check

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

Dimension 2

execution_time_seconds

Total elapsed execution time for full Crew workflow • target: 25 • range: 0-60

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

  • Design CrewAI agents with specific roles, goals, and domain tools

  • Set up sequential and hierarchical execution flows across maintenance crew roles

  • Verify material availability, crane permits, and hot-work safety protocols

  • Generate automated SAP-compatible Work Orders for execution crews

Resources and assets

Reference links and supporting material

Dataset notes

Synthetic dataset of 40 emergency damage reports for refinery units including catalytic crackers, distillation units, and pipelines.

Challenge setup

Evaluates completeness and safety compliance of generated emergency refinery work orders.

Challenge input

JSON payload detailing damage assessment and refinery unit ID

CrewAI

Ideal for role-playing autonomous agents collaborating on maintenance pipelines.

Evaluated output

JSON containing work order ID, required parts list, estimated repair hours, and safety permits

Evaluation checks
  • Ensures hot work permit flag is enabled for high severity heat repair tasks
  • Total elapsed execution time for full Crew workflow • target: 25 • range: 0-60
Configured evaluation evidence
  • Benchmark: OpsAgentBench
  • Execution Time Seconds target: 25
  • 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
  • Merge · Optional

Evaluation contract

  • safety_permit_included · Weight 1
  • execution_time_seconds · Weight 1

Metrics

  • execution_time_seconds · Target 25

Benchmarks

  • OpsAgentBench
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON payload detailing damage assessment and refinery unit ID

    Output: JSON containing work order ID, required parts list, estimated repair hours, and safety permits

    Execution harness: Python

Evaluation tools

  • CrewAI · Multi-Agent Orchestration

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Emergency Refinery Repair Operations Crew with CrewAI