Chinese-owned online travel platform Fliggy has unveiled the latest version of its agentic AI travel assistant, powered by Alibaba's Qwen model and built around Fliggy’s real-time transaction systems and proprietary travel scenario data. The upgraded assistant adopts a streamlined multi-agent architecture, moving beyond travel planning to complete complex multistep tasks such as arranging and changing bookings, including communicating with hotels about upgrades, checking availability, and coordinating options. It now has stronger memory capabilities, integrating users’ long-term preferences with real-time needs, and is embedded throughout the Fliggy app, accessible from the home screen to individual hotel detail pages. Users can describe complex travel requirements in natural language via voice or text, and the assistant works alongside traditional graphical user interface booking flows rather than replacing them. According to Fliggy data, the usability score of results delivered by the upgraded AI assistant has improved by more than 70% compared with its previous-generation product, while the average completion time for comparable tasks has been reduced by nearly 10%. Dr Alex Chen, CTO at Fliggy, said the upgrade represents a meaningful step in bringing AI capabilities into the physical world, changing how travellers interact with the platform and delivering real, actionable services across the entire journey. He added that AI agents will grow increasingly intelligent, moving beyond reactive assistance to offer proactive support across every stage of the journey.