·techlauncher, showcase
KoPilot at the 2024 ANU Computing Showcase
KoPilot wrapped up the semester at the 2024 ANU Computing Showcase, where the team demoed personalized travel recommendations for South Korea.
Read →
KoPilot
Notes on building Korea-local products: LLMs, geospatial data, and the realities of Korean map APIs.
KoPilot began as a travel assistant for visitors to South Korea, and later took part in the ANU TechLauncher program — the early posts are the record of that work.
What KoPilot works on now
The problem that started it — tourists can't easily get usable local recommendations — turned out to sit on top of a much deeper set of data and API problems. Those problems are now the substance of the project.
- Geospatial data pipelines — ingesting and normalizing Korean place data into queryable form
- Korean map API integration — the practical reality of building against Kakao and Naver
- LLM-backed local recommendations — grounding language models in real place data rather than training-set recall
Latest
All posts →·techlauncher, showcase
KoPilot travel assistant demo video
The KoPilot team's demo video from the 2024 ANU TechLauncher showcase: a walkthrough of the travel assistant app for visitors to South Korea.
Read →·techlauncher
KoPilot joins TechLauncher
KoPilot has been invited to the ANU TechLauncher program: what we are building, how the team is organised, and the work on offer across the stack.
Read →