Student: Christopher Lyko
Abstract:

Programmatic CAD systems allow users to define precise and reusable models through code, but they also require users to combine geometric reasoning with knowledge of a scripting language. Large Language Models create new opportunities to make programmatic CAD more accessible by translating natural-language design intentions into executable CAD scripts. However, AI-supported CAD generation does not remove the user from the design workflow. Generated results may be incomplete, incorrect, or misaligned with the user's intent, and design itself remains an iterative process of specifying requirements, creating alternatives, evaluating outcomes, and refining decisions.

Supporting this workflow requires attention to the forms of interaction through which users inspect, refine, and steer AI-generated results. Human-AI interaction patterns are therefore analyzed across AI-supported CAD modeling, AI-supported programming, and co-creative design systems to evaluate their relevance for programmatic CAD workflows. Based on this analysis, a selected subset of interaction patterns is implemented in a prototypical environment for AI-assisted OpenSCAD modeling. The prototype explores how users can generate, inspect, refine, understand, and steer CAD models in collaboration with an AI system while retaining control over code, parameters, and the rendered model.

The prototype is evaluated in a user study with beginner and experienced users. The study examines how the implemented interaction patterns affect the co-creation process, including the perceived quality of the resulting models, usability, perceived control, trust, and user satisfaction. A structured perspective on Human-AI interaction patterns for programmatic CAD is developed, leading to design implications for future AI-assisted CAD systems.
Email: christopher.lyko@tum.de
Status:

STARTING
Supervisor: David Fresacher 

1.1. Files

1.2. Documentation

1.2.1. Prototype Progress

1.2.1.1. 24.06. - 06.07.2026

Implemented: 

  • Conversational Refinement
  • Generative Variation Selection
  • Parameter-Based Refinement
  • AI-Proposal Review

1.2.1.2. 07.07. - 02.08.2026

Implemented:

  • Component Browser
  • Clarifying Questions
  • Design History
  • Explain with AI
  • Fixing Errors with AI
  • Inline Code Completions
  • Reflective Questions by AI
  • Adding Selections to AI

1.2.1.3.  03.08. - 16.08.2026

Implemented:

1.2.1.4.  17.08. - 25.08.2026

Implemented Evaluation Graphic Mocks

Checked expected costs of evaluation for following models by OpenAI:

  • Luna
  • Terra
  • Sol

Conclusion:

  • Use Luna in Tier 2
  • $50 in cumulative OpenAI API credits to unlock Tier 2
  • Consumption of about $1.83 for 20 participants
  • No noticeable difference to Terra and Sol to complete both tasks

Load Test with LLM-Stub

1.2.1.5.  26.08. - 31.08.2026

Added base projects for evaluation aftermath.

1.2.2. Paper Progress

1.2.2.1. 24.06. - 06.07.2026

  • Wrote Abstract, Introduction, Background

1.3. Workflow

1.3.1. Start

  • Topic specification
  • Definition of work packages
  • Composition of a project proposal and time plan
  • Project Talk with Prof. Diepold
  • Registration of the thesis
  • Creation of a wiki page (supervisor)
  • Creation of a gitlab repository or branch
  • Access to lab and computers

1.3.2. Finalization

  • Check code base and data
  • Check documentation 
  • Provide an example notebook that describes the workflow/usage of your code (in your repo)
  • Proof read written composition
  • Rehearsal presentation
  • Submission of written composition
  • Submission of presentation 
  • Recording of presentation / Presentation in group meeting
  • Final Presentation
  • No labels