AI Agent in VR Space
AI Agent in VR Space
Unity, C#, Python, LLM APIs, RAG, Prompt Engineering, VR
Period
2026
Duration
3.5 months
Team
6 people
Status
Academic prototype
Overview
Developed as a final 6th-semester group project, this VR application features a fully interactive AI agent designed to communicate with students and professors. The agent serves as a virtual guide and mentor, answering questions about the academic program and providing technical insights on VR, AR, and Unity development.
My Role & Core Systems As the LLM Developer, I used Python for LLM setup and C# for the Unity-side integration. I was responsible for the AI’s technical functionality, pipeline, and assistant behavior.
LLM Integration & Persona: Engineered the prompts and context windows to ensure the AI maintained a consistent, helpful persona that fits naturally into an academic VR environment.
RAG Architecture: Implemented a RAG pipeline to ground responses in project-specific reference material, including academic-program information and XR documentation.
Latency as a Development Challenge: Connecting external AI services to a VR application required attention to response latency during development.
The Challenge Bridging external AI pipelines with a VR application introduced latency and accuracy challenges during development. Structuring the reference material and connecting it to the Unity application required iteration to support useful, context-aware responses.
Overview
Developed as a final 6th-semester group project, this VR application features a fully interactive AI agent designed to communicate with students and professors. The agent serves as a virtual guide and mentor, answering questions about the academic program and providing technical insights on VR, AR, and Unity development.
My Role & Core Systems As the LLM Developer, I used Python for LLM setup and C# for the Unity-side integration. I was responsible for the AI’s technical functionality, pipeline, and assistant behavior.
LLM Integration & Persona: Engineered the prompts and context windows to ensure the AI maintained a consistent, helpful persona that fits naturally into an academic VR environment.
RAG Architecture: Implemented a RAG pipeline to ground responses in project-specific reference material, including academic-program information and XR documentation.
Latency as a Development Challenge: Connecting external AI services to a VR application required attention to response latency during development.
The Challenge Bridging external AI pipelines with a VR application introduced latency and accuracy challenges during development. Structuring the reference material and connecting it to the Unity application required iteration to support useful, context-aware responses.