ATPCO completes proof of concept for AI travel request matching to airline products

On October 9, 2026, PhocusWire reported that ATPCO completed a two-week proof of concept exploring how to match traveler requests expressed in everyday language to the structured airline data needed to identify relevant products. ATPCO Vice President of Technology Anand Mishra said AI assistants can already understand traveler demands, and the difficulty lies in linking intent to structured data, for example mapping the semantic meaning of "comfortable seat" to a seat map. The proof of concept also tested how to return results when travelers provide images rather than text, with data sources including Routehappy, which provides visual and product attribute details. Current progress: the proof of concept has been completed.