HotelPlanner: How AI and human booking agents can thrive together

What does it take to recreate real world personalized customer service delivery through AI? In HotelPlanner’s case, no less than eight million calls.

Speaking to Globetrender, Tim Hentschel, co-founder and co-CEO of HotelPlanner explained the evolution of HotelPlanner.ai, a first of its kind AI powered hotel booking assistant.

“We used data from over eight million calls to train AI voice assistants to not only look after our customers many queries but sell rooms in a streamlined, enjoyable and efficient experience.”

“This has never been seen before.”

Several years in development, HotelPlanner.ai is far advanced from the standard and fairly limited AI chatbot experience of recent years.

“Our mission was to find something that could enhance the customer experience from a speed and convenience perspective. This platform wouldn’t be possible without working with the best partners in the business – for example the best partners for large language modules, voice recognition and more,” Hentschel said.

He describes HotelPlanner.ai the first end-to-end AI hotel booking assistant. It responds to customer requirements, checks the availability and prices suitable rooms. It can succinctly explain the booking terms and also process a credit card booking.

It currently has fluency in 15 languages. Greek, Turkish and many more languages are expected to be added soon.

Here’s how HotelPlanner leveraged those eight million calls from its gig economy call center to fine tune and personalize the service.

“Through the analysis of those call transcripts and audio recordings, these systems have learnt how to handle various queries, accents and dialects. They’re adapted to deal with ambiguity, understand natural language, and make highly personalised responses.”

“We’re now seeing over 45,000 calls taken per day, and with each call the platform learns more and more about human interaction.”

Before the rollout of HotelPlanner.ai, call volumes were around 25,000 a day.

“Our booking agents speak fluently in 15 languages, all of which have been programmed to offer humanised conversations with customers,” he added.

“We actually don’t even introduce the agents as AI on the call, and recorded transcripts point towards come customers having no idea they aren’t talking to a human.”

Hentschel doesn’t buy into the theory that AI is a threat to jobs.

“The AI agents are constantly learning but at present they are best suited to take the simpler booking requests. This is why we have our gig-agents, and why I often refute claims that AI is bad from a job perspective. Our agents take the higher value calls, allowing them to make more money per conversation.”

In fact, both the AI and human agent roles can co-exist in harmony, each playing to their own strengths.

“With AI now able to handle the majority of less advanced requests, it means that our human agents are much less stretched, and able to pick up a greater volume of more advanced booking queries.”

“This means that with the combination of the AI agents and human gig-economy, our booking platform is running more efficiently than ever, serving the highest number of customers we’ve ever seen, in the shortest about of time,” Hentschel added.

Related News Stories:  HotelPlanner unveils world's first end-to-end AI hotel booking assistant     Hotelplanner - TravelMole     Hotelplanner.com acquires TravelMole, expanding global reach and ...     Marriott announces tech accelerator in India     Hyatt completes Standard International acquisition     Kittipong Prapattong's Plan for Thailand's Tourism Growth: Taxes ...     World Travel Agents Associations Alliance appoints new leadership     Carnival expands 2026/27 programme with new sailings from Miami ...     TravelMole     Punta Gorda tourism back in business after hurricane