Back to challenges
Challenge

Engineering Intelligence CAD Analysis Pipeline with Claude Agents SDK and Google Jules

Static CAD designs lack automated thermal and stress validation, delaying manufacturing engineering reviews. Build an engineering intelligence agent using Claude Agents SDK and Google Jules to analyze STEP file metadata and automated FEA summaries. Ensure 90% accuracy in identifying manufacturability defects before physical prototyping.

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 intelligent CAD inspection agent using Claude Agents SDK and Google Jules to evaluate manufacturing tolerances and design parameters.

Delivery guide

How work is evaluated

Evaluation

Validate agent's capability to read parametric CAD metadata and accurately flag manufacturing risks and tolerance violations.

Datasets

Shared data for this challenge

Review public datasets and any private uploads tied to your build.

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

defect_detection_pass

Detects all high-risk design flaws in benchmark dataset

Binary check

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

Dimension 2

dfm_accuracy

Accuracy of identified manufacturability issues • 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

  • Build a file processing agent to extract geometric and material features from CAD/STEP export summaries

  • Utilize Claude Agents SDK with extended thinking to identify thermal and mechanical flaw risks

  • Integrate Google Jules AI engineering tools to generate actionable code fixes for parametric CAD files

  • Produce automated Design-for-Manufacturability (DFM) compliance reports

Resources and assets

Reference links and supporting material

Dataset notes

Parametric metadata summaries of 50 mechanical CAD parts including stress limits, wall thicknesses, fillet radii, and material specs.

How this agent runs

Validate agent's capability to read parametric CAD metadata and accurately flag manufacturing risks and tolerance violations.

Challenge input

JSON object describing wall thickness, material, and geometric constraints

Claude Agents SDK

Provides reasoning and execution workflow.

Google Jules

Automates structural refactoring scripts.

Evaluated output

JSON report listing detected_defects, risk_score, and recommended_design_change

Checks for
  • Detects all high-risk design flaws in benchmark dataset
  • Accuracy of identified manufacturability issues • target: 0.9 • range: 0-1
Proof of success
  • Benchmark: CAD Design for Manufacturability Benchmark
  • Dfm Accuracy target: 0.9
  • 1 public reference case
Runtime evidence
  • Python execution harness
  • Python sandbox (unavailable on Versalist)
View technical recipe

Configured tools

Action Space
  • Google Jules · Required
  • Google · Optional
  • Claude Code · Optional
Observation
  • Claude Code · Optional
Orchestration
  • Google Jules · Required

Evaluation contract

  • defect_detection_pass · Weight 1
  • dfm_accuracy · Weight 1

Recipe state

This is a preview. The configuration can change before the evaluation recipe is locked.

Frequently Asked Questions about Engineering Intelligence CAD Analysis Pipeline with Claude Agents SDK and Google Jules