# "I Just Need GPT to Refine My Prompts": Rethinking Onboarding and Help-Seeking with Generative 3D Modeling Tools

arXiv: https://arxiv.org/abs/2603.29118 · HTML: https://mlsanity.com/paper/2603.29118/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 26 of its 87 references that are in the map.
- First posted on arXiv 31 Mar 2026.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 26 of 26)

- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [DreamFusion: Text-to-3D using 2D Diffusion](https://mlsanity.com/paper/2209.14988/) (2022)
- [Magic3D: High-Resolution Text-to-3D Content Creation](https://mlsanity.com/paper/2211.10440/) (2022)
- [Instruction-Following Evaluation for Large Language Models](https://mlsanity.com/paper/2311.07911/) (2023)
- [Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations](https://mlsanity.com/paper/1906.01618/) (2019)
- [Shap-E: Generating Conditional 3D Implicit Functions](https://mlsanity.com/paper/2305.02463/) (2023)
- [The Impact of AI on Developer Productivity: Evidence from GitHub Copilot](https://mlsanity.com/paper/2302.06590/) (2023)
- [Grounded Copilot: How Programmers Interact with Code-Generating Models](https://mlsanity.com/paper/2206.15000/) (2022)
- [When combinations of humans and AI are useful: A systematic review and meta-analysis](https://mlsanity.com/paper/2405.06087/) (2024)
- [Art and the science of generative AI: A deeper dive](https://mlsanity.com/paper/2306.04141/) (2023)
- [3DALL-E: Integrating Text-to-Image AI in 3D Design Workflows](https://mlsanity.com/paper/2210.11603/) (2022)
- [How Knowledge Workers Think Generative AI Will (Not) Transform Their Industries](https://mlsanity.com/paper/2310.06778/) (2023)
- [Why and When LLM-Based Assistants Can Go Wrong: Investigating the Effectiveness of Prompt-Based Interactions for Software Help-Seeking](https://mlsanity.com/paper/2402.08030/) (2024)
- [The Effects of Generative AI on Computing Students' Help-Seeking Preferences](https://mlsanity.com/paper/2401.02262/) (2024)
- [Prompts Are Programs Too! Understanding How Developers Build Software Containing Prompts](https://mlsanity.com/paper/2409.12447/) (2024)
- [An Empirical Study of Obsolete Answers on Stack Overflow](https://mlsanity.com/paper/1903.12282/) (2019)
- [Practices and Challenges of Using GitHub Copilot: An Empirical Study](https://mlsanity.com/paper/2303.08733/) (2023)
- [fAIlureNotes: Supporting Designers in Understanding the Limits of AI Models for Computer Vision Tasks](https://mlsanity.com/paper/2302.11703/) (2023)
- [Generative AI in Knowledge Work: Design Implications for Data Navigation and Decision-Making](https://mlsanity.com/paper/2503.18419/) (2025)
- [What Makes a Good Natural Language Prompt?](https://mlsanity.com/paper/2506.06950/) (2025)
- [Deep3DSketch: 3D modeling from Free-hand Sketches with View- and Structural-Aware Adversarial Training](https://mlsanity.com/paper/2312.04435/) (2023)
- [Expanding the Generative AI Design Space through Structured Prompting and Multimodal Interfaces](https://mlsanity.com/paper/2504.14320/) (2025)
- [Progress and Prospects in 3D Generative AI: A Technical Overview including 3D human](https://mlsanity.com/paper/2401.02620/) (2024)
- [Invisible Labor in Open Source Software Ecosystems](https://mlsanity.com/paper/2401.06889/) (2024)
- [Digital Labor and the Inconspicuous Production of Artificial Intelligence](https://mlsanity.com/paper/2410.05910/) (2024)
- ["All Roads Lead to ChatGPT": How Generative AI is Eroding Social Interactions and Student Learning Communities](https://mlsanity.com/paper/2504.09779/) (2025)

## Abstract (arXiv)

Learning to use feature-rich software is a persistent challenge, but generative AI tools promise to lower this barrier by replacing complex navigation with natural language prompts. We investigated how people approach prompt-based tools for 3D modeling in an observational study with 26 participants (14 casuals, 12 professionals). Consistent with earlier work, participants skipped tutorials and manuals, relying on trial and error. What differed in the generative AI context was how and why they sought support: the prompt box became the entry point for learning, collapsing onboarding into immediate action, while some casual users turned to external LLMs for prompts. Professionals used 3D expertise to refine iterations and critically evaluated outputs, often discarding models that did not meet their standards, whereas casual users settled for "good enough." We contribute empirical insights into how generative AI reshapes help-seeking, highlighting new practices of onboarding, recursive AI-for-AI support, and shifting expertise in interpreting outputs.