This is the working prototype of the mobile application, built on a Retrieval-Augmented Generation (RAG) workflow. The interface was designed in Figma, and deployment is currently in progress.
Griptape RAG+ ComfyUI /Flux + LLM + Gpt40, GPT4.1 + Custom Lora Training + Hunyuan 3D + APIs + Karamba Grasshopper + Figma + VScode + PyCharm
formatAI for Circular Economy
Category- MS Architectural technologies
Location- SCI-Arc, Los Angeles, CA
Year- Thesis Prep, Spring 2025
Type- Individual
Could one click turn your scrap into a detailed design- decarbonizing at its root in seconds?
Format transforms construction waste into usable designs, with step by step built instructions and assembly diagrams. It’s about fast, iterative composition that turns waste into form.
The project aims at closing the gap between design and technology by leveraging AI in topics such as the circular economy, strengthening the design workflow for a generation that prefers to do things with one click—ideally from the couch.
This is an independent academic research work in progress, exploring other materials, methods, and scales. Descoping at the product scale to crack the logic, with the goal to diversify across architecture, fashion, and other potential domains.
All the designs in the video use waste cardboard paper as their image input. Each output is a buildable architectural form generated in a single click, complete with assembly diagrams and logical construction sequencing. All designs were developed using the RAG workflow, grounded in fabrication-aware logic.
The following images are examples of step-by-step visual guides generated using LLMs and image generation tools on Flux Kontext. The goal is to continue refining this workflow to achieve greater accuracy and reliability. The current results are quite satisfactory, though there remains room for improvement.
Studio Instructor-
Casey Rehm
Case miller