Spotnana is introducing “multi-agent AI architecture” to its platform, with new automations for travel agents and new tools for travellers and travel managers.
Expected to be available later this year, the new AI architecture is open by design, allowing its customers and partners to develop their own AI agents and integrate Spotnana’s AI capabilities with other systems.
Being introduced in phases, the first set of AI capabilities will focus on helping agents get rid of highly repetitive and time consuming tasks.
The technology, developed over the last year, will automate refunds, cancelled segments that result from airline schedule changes and validate unticketed airline.
The AI agents will also bring externally booked trips into the Spotnana platform.
Spotnana will also be able to provide AI-driven, including analytics on completed servicing tasks and data on the volume of tasks completed by the AI servicing agent, along with AI-generated insights on trends and suggested actions.
Other features will be announced in the coming months.
“For years we have worked to automate every servicing workflow across every source of content, so travellers could do more without asking an agent for help,” said Ashish Chaudhary, Executive Vice President of Engineering at Spotnana.
“Our AI architecture builds on that foundation and extends it even further, opening the door to a new generation of traveller experiences.”
Yash Doshi, Spotnana Director of Product Management, said: “AI has tremendous potential to fundamentally change how travel is booked, managed, distributed, and serviced. While the opportunity is enormous, there are many approaches to implementing AI, and we wanted to ensure the path we took would provide the best long-term benefits for our customers and partners.
“It’s easy to make an AI demo look flashy. It’s much harder to make AI highly functional, reliable, and enterprise-grade.”
Giving deeper insight into Spotnana’s approach, he outlined four key layers:
- Engagement layer – the layer that defines what a user can see and interact with. The travel industry is moving towards a conversational user experience that is consumable through an OBT and in additional channels like Slack and Teams.
- Agent management layer – once a request is received by an AI agent at the engagement layer, it needs to be broken down into tasks that are performed deeper in the stack or by a live travel agent.
- Action layer – the action layer is where tasks are performed on behalf of the user. The impact of AI is ultimately determined by the number of workflows that can be automated across different travel modalities (air, hotel, etc.) and content sources.
- Data layer – the ability of AI to make useful, accurate recommendations to a trave;ler and provide actionable insights is also determined by the breadth, structure, and accuracy of the underlying data. Without high quality data, AI is operating on pillars of sand.
Doshi added: “Rather than relying on a single general-purpose assistant, Spotnana has built a multi-agent AI architecture that uses specialised AI agents to perform discrete tasks.
“Each AI agent is mapped to specific Spotnana APIs that execute deterministic workflows, resulting in a high degree of accurate, autonomous action.
“In our architecture, an AI agent can never invent a refund amount, a fare rule, or a travel policy – it can only execute the same governed operations a human would take using the same structured data and automated workflows.”
