Fliggy becomes next travel platform to reveal its agentic AI assistant

Built on a travel-tuned Qwen foundation model, it plans, books, and manages trips for users

Chinese-owned online travel services platform, Fliggy, has unveiled the latest version of its agentic AI travel assistant designed for personalized and direct task implementation, further upgrading its consumer-facing AI capabilities.  

The upgraded assistant is now agentic-ready, powered by Alibaba's Qwen model - as Fliggy is part of the Alibaba Group - and built around Fliggy’s real-time transaction systems and proprietary travel scenario data.

It now adopts a streamlined multi-agent architecture that consolidates specialised agents and an expanded set of tools into one system. 

In this new rollout, it moves beyond travel planning and recommendations to now be able to complete complex multistep travel tasks including arranging and changing bookings. 

The AI assistant can communicate with the hotel about an upgrade, check availability, co-ordinate options and provide updates which could certainly be one of the most advanced AI assistants on the market at the moment for travellers.

Its update also sees it now have stronger memory capabilities, enabling it to better integrate users’ long-term preferences with their real-time needs, deliver more relevant solutions, and provide increasingly personalised support to Fliggy’s customers. 

Embedded throughout the Fliggy app, it is easily accesible for travellers to use from the home screen all the way down to a single hotel's detail page and users can describe complex travel requirements in natural language through voice or text commands. 

It's been designed to work alongside traditional graphical user interface booking flows instead of replace - users can either book through familiar interfaces or delegate tasks to it for execution across the platform. 

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: “This upgrade represents a meaningful step in bringing AI capabilities into the physical world. It fundamentally changes how travellers interact with our platform: users can now express personalised needs in natural language while our agentic AI assistant delivers real, actionable services across the entire journey – from trip planning and in-trip services to post-travel assistance. 

"Looking ahead, as AI technology matures and the travel ecosystem continues to embrace it, we believe AI agents will grow increasingly intelligent, moving beyond reactive assistance to offer proactive support across every stage of the journey." 

Based on the architecture its built upon, it's to be expected that Fliggy will continue to develop, adding new capabilities, and continuously improving alongside advances in foundation models, as time goes on.