Skip to main content
Back to challenges
Challenge

Interactive Control Engineer Mentor Chatbot using AutoGen

Control engineers stepping outside their traditional PLC comfort zones require an interactive, conversational mentor that guides them through cloud architecture, API design, and modern devops. In this challenge, developers will create a two-agent AutoGen conversation pairing a Senior Cloud Automation Architect with a Control Engineer User Proxy.

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 an AutoGen pair-programming chat system to assist control engineers in migrating ladder logic to cloud microservices.

Delivery guide

How work is evaluated

Evaluation

Evaluates the accuracy of educational code suggestions provided by the AutoGen assistant agent.

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

MQTT Code Accuracy

Generated code must include valid paho.mqtt code structure

Binary check

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

Dimension 2

Explanation Clarity Score

Assessment of step-by-step guidance provided in textual response • target: 0.9 • 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

  • Set up a dynamic AutoGen two-agent conversation (`AssistantAgent` & `UserProxyAgent`)

  • Configure contextual system messages tailored for control engineers

  • Implement automatic code execution for Python control script examples

  • Guide users through transitioning ladder logic into event-driven software

Resources and assets

Reference links and supporting material

Dataset notes

Curated set of 20 technical transition questions asked by control engineers moving into AI/software roles.

Challenge setup

Evaluates the accuracy of educational code suggestions provided by the AutoGen assistant agent.

Challenge input

User message string asking for MQTT publisher snippet

AutoGen

Assigned framework

Evaluated output

Assistant response containing valid Python paho-mqtt snippet

Evaluation checks
  • Generated code must include valid paho.mqtt code structure
  • Assessment of step-by-step guidance provided in textual response • target: 0.9 • range: 0-1
Configured evaluation evidence
  • Benchmark: Educational Coding Assistant Benchmark
  • Explanation Clarity Score target: 0.9
  • 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

  • MQTT Code Accuracy · Weight 1
  • Explanation Clarity Score · Weight 1

Metrics

  • Explanation Clarity Score · Target 0.9

Benchmarks

  • Educational Coding Assistant Benchmark
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: User message string asking for MQTT publisher snippet

    Output: Assistant response containing valid Python paho-mqtt snippet

    Execution harness: Python

Evaluation tools

  • AutoGen · Conversational framework

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Interactive Control Engineer Mentor Chatbot using AutoGen