Skip to main content
Back to challenges
Challenge

Module Type Package (MTP) Plug-and-Produce Automation Orchestrator using CrewAI

Process plants struggle with modular reconfiguration when integrating multi-vendor equipment without standardized Module Type Package (MTP) definitions. Build a plug-and-produce orchestrator using CrewAI to parse module descriptors, validate OPC UA interface mappings, and automate orchestration across process units.

EngineeringHosted by Vera
Sign in free to start
Challenge brief

What you are building

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

Build a CrewAI multi-agent team to parse MTP manifest files and orchestrate automated plug-and-produce connections between process modules.

Delivery guide

How work is evaluated

Evaluation

Evaluates MTP manifest mapping completeness and generated Process Orchestration Layer bindings.

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

Validation Error Test

Ensures zero validation errors for compliant MTP inputs.

Binary check

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

Dimension 2

bound_services_ratio

Ratio of correctly bound MTP services to requested services. • target: 1 • 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

  • Define CrewAI agents (MTP Parser Agent, OPC UA Binding Agent, Operations Manager)

  • Automate manifest validation for VDI/VDE/NAMUR 2658 Module Type Package standards

  • Synthesize Process Orchestration Layer (POL) configuration outputs automatically

Resources and assets

Reference links and supporting material

Dataset notes

Sample MTP manifest files (VDI/VDE/NAMUR 2658 compliant) for dosing, mixing, and heating modular process units.

Challenge setup

Evaluates MTP manifest mapping completeness and generated Process Orchestration Layer bindings.

Challenge input

JSON containing module_id, mtp_version, services_provided

CrewAI

Offers structured multi-agent role play and tool execution.

Evaluated output

JSON with pol_bound_nodes, state_machine_status, and validation_errors

Evaluation checks
  • Ensures zero validation errors for compliant MTP inputs.
  • Ratio of correctly bound MTP services to requested services. • target: 1 • range: 0-1
Configured evaluation evidence
  • Benchmark: Modular Process Automation Benchmark
  • Bound Services Ratio target: 1
  • 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

  • Validation Error Test · Weight 1
  • bound_services_ratio · Weight 1

Metrics

  • bound_services_ratio · Target 1

Benchmarks

  • Modular Process Automation Benchmark
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON containing module_id, mtp_version, services_provided

    Output: JSON with pol_bound_nodes, state_machine_status, and validation_errors

    Execution harness: Python

Evaluation tools

  • CrewAI · Agent Collaboration Framework

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Module Type Package (MTP) Plug-and-Produce Automation Orchestrator using CrewAI