Skip to main content
Back to challenges
Challenge

Software-Defined Controls (SDC) Testing Agent with Pydantic AI

Software-defined controls require strict type-safe automated testing to prevent runtime PLC crashes. Create a deterministic control software testing harness using Pydantic AI to validate IEC 61131-3 logic against edge simulation models. Ensure 100% type-safe payload validation and zero unhandled exceptions during execution.

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 type-safe test runner agent using Pydantic AI to validate software-defined control logic against physical boundary conditions.

Delivery guide

How work is evaluated

Evaluation

Evaluate test generation agent's output against expected type constraints and test coverage criteria.

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

pydantic_schema_valid

Output passes Pydantic runtime schema validation

Binary check

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

Dimension 2

test_coverage

Coverage of specified control loop edge cases • 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

  • Build type-safe control validation models using Pydantic and Pydantic AI

  • Implement test case generation for software-defined control loops (PID, state machines)

  • Enforce rigorous validation on telemetry input/output data ranges

  • Generate automated compliance certificates for edge deployment

Resources and assets

Reference links and supporting material

Dataset notes

Control loop parameter specifications and physical limits for SDC testing.

Challenge setup

Evaluate test generation agent's output against expected type constraints and test coverage criteria.

Challenge input

JSON object describing PID loop setpoints and tolerance limits

Pydantic AI

Guarantees strict schema validation for model outputs.

Evaluated output

JSON test report detailing pass/fail results for edge test vectors

Evaluation checks
  • Output passes Pydantic runtime schema validation
  • Coverage of specified control loop edge cases • target: 1 • range: 0-1
Configured evaluation evidence
  • Benchmark: Type-Safe Agent Verification Benchmark
  • Test Coverage 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
  • Pydantic AI · Required
Orchestration
  • Pydantic AI · Required

Evaluation contract

  • pydantic_schema_valid · Weight 1
  • test_coverage · Weight 1

Metrics

  • test_coverage · Target 1

Benchmarks

  • Type-Safe Agent Verification Benchmark
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON object describing PID loop setpoints and tolerance limits

    Output: JSON test report detailing pass/fail results for edge test vectors

    Execution harness: Python

Evaluation tools

  • Pydantic AI · Type-Safe Agent Framework

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Software-Defined Controls (SDC) Testing Agent with Pydantic AI