Want to know more?
Are you interested in this project? Or do you have one just like it? Get in touch. We’d love to tell you more about it
How Travelopia improved customer wait time from 24 hours to instant with GenAI
By introducing GenAI to their Travel Coordinator service, Travelopia reduced response times and enhanced the quality of information available to customers
Enchanting Travels is a travel brand owned by Travelopia. They provide highly tailored travel experiences, and enhance their customers’ experience by allocating a dedicated Travel Coordinator to every customer. The turnaround time for communication between coordinator and customer, before Equal Experts’ engagement, was previously around 24 hours.
Travelopia wanted to improve communication between coordinators and the customer, and thus the customer experience, by implementing a real-time chatbot.
Using an existing chatbot as a basis, we modified and added to the data available, retaining the original format. We were able to roll out a pilot version to a small number of coordinators within 7 days. After only a few weeks the entire team of Travel Coordinators were using this solution.
The chatbot functions similarly to ChatGPT, instantly retrieving information and providing links to relevant documents needed by the coordinator when a customer has an inquiry. This has reduced customer waiting times from 24 hours to instant, enhanced the quality of information provided and has set the stage for further implementation of GenAI within Travelopia.
Outcomes
2 weeks
to release a pilot chatbot
24 hours to instant
customer wait times drastically reduced
About Travelopia
Travelopia is the home for brands that create extraordinary travel experiences. They are at the forefront of global travel for those wanting something distinctive. Travelopia’s focus is specialist travel experiences, such as yachting, safaris and luxury travel. Their brands are diverse and exciting, creating unforgettable experiences for customers across the world.
Industry
Travel and transport
Size
1500 employees, approximately $1b revenue
Location
Global
Length of project
2 weeks
Challenge
Building a GenAI chatbot to revolutionise and enhance customer service
Enchanting Travels allocates each of its customers with a dedicated travel coordinator to provide a tailored service. Under the previous system, a coordinator would receive a query from their customer, search for the answer in a variety of places, and then reply to the customer. This process took an average of 24 hours. Travelopia wanted to optimise the efficiency of this service, and knew there was scope within this project to utilise the capabilities of GenAI.
Travelopia approached Equal Experts to support the implementation of a new real-time chatbot named Athena. Athena was to be used by internal staff, with the goal of reducing response times and improving the quality of the information being provided, thereby increasing customer satisfaction. It was also expected that Athena would optimise the time of the travel coordinators, and save on costs for Enchanting Travels.
Solution
Maximising the full scope and potential of a GenAI chatbot: The path to production
Equal Experts has previously engaged with Travelopia on a number of successful projects, which prompted the decision to work together again on this particular opportunity. When Equal Experts arrived at this engagement, Travelopia was already utilising a chatbot for a different brand. Although the chatbot was similar in nature to the one Enchanting Travels needed, it was developed as a proof-of-concept by internal Travelopia staff. Although the chatbot did function adequately, there was limited effort put into refinement, completeness, and implementing the full scope and potential of the chatbot.
Equal Experts used the existing chatbot as a starting point, but to meet the requirements of Enchanting Travels, we needed to add more data sources to the chatbot to automate data ingestion, and ensure all the information held was searchable and retrievable. These were to be found in the original documents the coordinators would previously have manually searched to find information, and were available in many formats including PDFs and spreadsheets.
The addition of these extra data points for the chatbot served to increase the accuracy of the responses, and allowed for citations and justifications for those results. The data is kept up to date and in sync by an internal team within Travelopia who simply upload documents to a cloud storage bucket (AWS S3), from which the data is then extracted automatically.
We began by writing a connector for each document type (PDF, Excel, PPT, etc.) that could read and interpret the data and store it within the LLM (therefore building context for the chatbot.) However, this has now been replaced by AWS Knowledge Base, which can automatically identify each file type, pass it through the LLM and store it accordingly. This effectively removes a lot of the manual developer effort involved in the process, and doesn’t require adaptation of original files. Although this didn’t present any real challenges, we were careful to trial various methods and models for accuracy and efficiency of results to reduce response time. We also made some visual alterations to the interface of Athena to reflect the Enchanting Travels brand.
The chatbot’s responses were validated with manual testing. We referred to documents and outlined questions to check if the chatbot was responding with the expected answers. Since this was an internal tool, we were able to capture feedback from end users via weekly reports and a ‘thumbs up’ or ‘thumbs down’ reaction for the chatbot’s response.
A user-friendly, intuitive, and speedy customer service tool
In terms of functionality, the front end is similar to Chat GPT. The coordinator enters the customer’s question and Athena locates and presents the information immediately, alongside links to any documents in which the data is stored. It holds context throughout an interaction, so coordinators can request further information to narrow results if necessary.
The product captures and retains data around what information is being requested and whether requests are successfully fulfilled, which can be used to identify gaps in the knowledge base and enrich the data available.
A pilot version of Athena was rolled out to a limited number of users within seven days.
The data is currently being ingested monthly by Athena, but this can be increased if necessary. We are now exploring ways of working with AWS, which would allow a fully automated method of Athena identifying and ingesting data.
Results
Reducing response times by 100% while still maintaining human interaction
The successful implementation of Athena has radically improved response times, from a 24-hour wait to an immediate response. The time saved by coordinators allows them to assist more customers, increasing both staff and customer satisfaction. It has also increased the quality and reliability of the information available.
Travelopia has introduced Athena intentionally as an internal tool, recognising the value their customers place on human interaction. They have introduced GenAI to this process in an appropriate, responsible, and thoughtful way.
Driving digital innovation and excellence
The swift and effective implementation of a new GenAI chatbot to be used as an internal tool for travel coordinators has been a huge success for Travelopia. It has improved customer service, saved the organisation money and paved the way for further adoption and utilisation of GenAI for the business and its many luxury brands.
The switch to AWS has reduced the effort required to add and maintain data, and switching between different Gen AI models has also reduced the response time from around 30 seconds to approximately 3 seconds. This not only provides a more immediate resolution for customers, it also allows travel coordinators more time to focus on tailoring the travel perfect experience for their customers.
The implementation of Athena is an innovative first step in Travelopia’s journey into the adoption of GenAI. Due to Athena being an internal tool, it was seen as a relatively safe proof-of-concept, and Travelopia is hopeful this will lead to further use of technology as a tool to enhance ways of working.