Ontology in the Age of AI
Ontology in the Age of AI
The author describes building an ontology and validated prediction model for Australian aged care accommodation pricing, which an AI agent then uses to answer regulator questions without fabricating data, in a sector where room prices above A$789,686 require government approval backed by evidence. The piece covers ontology definitions from Gruber (1993) and Noy & McGuinness (2001), a worked retail example, the aged care ontology design journey, and cautions about black-box predictions, data leakage on third-party LLM platforms, and token-based costs. It concludes with takeaways including that LLMs can be swapped but the ontology and validated model cannot, and that ontology should be designed before the AI agent is developed.
Source: Hacker News AI · safdarali2.substack.com