Skip to main content
Back to challenges
Challenge

Control Systems Engineering Upskilling Simulator with CrewAI

Upskilling junior control engineers to operate modern software-driven automation systems requires hands-on interactive scenario evaluations. Build a multi-agent training simulator using CrewAI where dynamic instructor and evaluator agents challenge students with live control logic debugging tasks. Achieve an objective score grading consistency rate of 95% across training scenarios.

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.

Construct an interactive control engineering training sandbox using CrewAI agents to generate, grade, and feedback PLC debugging scenarios.

Delivery guide

How work is evaluated

Evaluation

Evaluates consistency and quality of automated grading feedback provided on student control code submissions.

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

passing_evaluation

Ensure student code fix is scored accurately above pass threshold

Binary check

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

Dimension 2

grading_consistency

Consistency score of automated AI evaluator relative to expert panel key • target: 0.95 • 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

  • Design CrewAI agents representing Instructor, Code Evaluator, and Feedback Coach

  • Simulate fault injection scenarios in industrial control code (e.g., race conditions, deadlock)

  • Provide objective grading feedback with actionable recommendations

Resources and assets

Reference links and supporting material

Dataset notes

Collection of 20 industrial control bug scenarios and verified student submission samples.

Challenge setup

Evaluates consistency and quality of automated grading feedback provided on student control code submissions.

Challenge input

JSON containing injected bug scenario and student code submission

CrewAI

Enables multi-agent role play between instructor and code evaluator roles.

Evaluated output

JSON evaluation score (0-100) and structured feedback summary

Evaluation checks
  • Ensure student code fix is scored accurately above pass threshold
  • Consistency score of automated AI evaluator relative to expert panel key • target: 0.95 • range: 0-1
Configured evaluation evidence
  • Benchmark: Control Engineering Education Suite (EDU-CTRL-2025)
  • Grading Consistency target: 0.95
  • 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

  • passing_evaluation · Weight 1
  • grading_consistency · Weight 1

Metrics

  • grading_consistency · Target 0.95

Benchmarks

  • Control Engineering Education Suite (EDU-CTRL-2025)
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON containing injected bug scenario and student code submission

    Output: JSON evaluation score (0-100) and structured feedback summary

    Execution harness: Python

Evaluation tools

  • CrewAI · Agent Framework

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Control Systems Engineering Upskilling Simulator with CrewAI