01
Aviation Track winners, Agentic AI Build Week
An award-winning aviation maintenance platform that forecasts aircraft-tire wear, prioritizes interventions, and gives line engineers an agent grounded in fleet data and maintenance manuals.
Work
Systems built to move
from possibility to practice.
A selection of AI agent platforms, simulation tooling, and language-model research. Each case study focuses on the problem, the choices, and what the work made possible.
02
Vivu — AI Photo Editing for Travel Memories
A production AI photo-editing product that helps travelers remove people and distractions through intelligent selection, iterative editing, and a guided browser-first experience.
03
Coding Agent for Data Science
An extensible coding agent that helps data teams turn natural-language requests into executable analysis across platform data and connected databases.
04
AI-powered CAD Document Processing Platform
A multimodal system for processing, retrieving, and analyzing manufacturing specifications, Bills of Materials, and complex 2D and 3D CAD files.
05
Asset Risk Assessment — Real-estate Analysis Platform
An MVP platform that retrieves and enriches real-estate information from documents and multiple external data sources for asset risk analysis.
06
OSG-Q3 — Robust OpenSCENARIO Generation with LLMs
A simulator-aware framework that turns natural-language ADAS requirements into executable OpenSCENARIO scenarios through structured generation, deterministic conversion, and simulation-based evaluation.
07
Testing Traffic Scenario Generation Pipeline in ADAS
A production-oriented pipeline that turns user-written ADAS test descriptions into traffic scenarios executed in CARLA with observable LLM workflows.
08
Vietnamese Text-to-SQL with Large Language Models
Research into adapting large language models to translate Vietnamese questions into executable SQL using fine-tuning and in-context learning.
A note on the case studies
These stories are living documents. The core scope is here; measurable outcomes, diagrams, and deeper technical decisions will be added as the supporting material is prepared.