Enhancing Airline Customer Support with Generative AI and AWS Contact Centers
Shweta, a weary traveler, sat in a stationary train, a sense of urgency and frustration building within her. Her destination was the airport, where her morning flight was scheduled to take off. However, a signal failure had brought her train to an abrupt halt in an unfamiliar station.
The train’s unexpected pause left Shweta with a sinking feeling; her tight schedule was unraveled. She knew that, at this rate, she would never make it to the airport in time to catch her flight. With minutes slipping away, she knew her best hope was to seek help from the airline’s customer support.
Desperate to reschedule her flight to a later departure, she reached for her phone and dialed the airline’s customer support number. The phone rang repeatedly, its persistent tone a stark reminder of her vanishing hopes. She needed an agent to assist her, and yet there was no one on the other end to answer her call.
Frustration welled up inside Shweta as she listened to the unanswered ring. Her need for assistance was dire. The next available flight, departing two hours after her original schedule, was her only chance to make her journey. The minutes ticked away, leaving her with no option but to watch the train sit idle.
Inside the airline’s call center, there was a palpable absence of agents to answer the surging number of early morning calls. The station’s signal failure, a mere technical glitch, had unknowingly thrown the lives of countless travelers, including Shweta, into disarray.
Her long and frustrating wait in the station served as a vivid reminder of the necessity for airlines to embrace technological solutions, especially during the early morning hours when passengers like her faced unexpected delays.
Airline’s customer support team was no stranger to the challenges they face daily. Customer inquiries floods in through various channels, including phone calls, chats, and emails. Long wait times and generic responses keep customers frustrated, and now leveraging Generative Ai will help the airlines to change. With the emergence of Generative AI, Airlines can embark on a transformative journey to create a cutting-edge contact center using AWS Contact Center and Generative AI in addressing such situations promptly and efficiently.
AWS Contact Center helps airlines to revamp their customer care contact center. They can leverage Amazon Connect to set up a cloud-based infrastructure, enabling seamless call routing and agent workspaces. The airline’s management team will be delighted by the scalability and flexibility of AWS, knowing they could handle surges in call volumes during peak travel seasons.
Generative AI is a type of AI powered by machine learning (ML) models that are trained on vast amounts of data and are used to produce new content, such as photos, text, code, images, and 3D renderings.
To enhance customer interactions, the airline can integrate generative AI capabilities into their contact center using AWS services. They can deploy Amazon Lex, a powerful NLP service, to build intelligent virtual agents. These virtual agents can be trained to understand natural language and provide human-like responses. They were designed to handle a wide range of inquiries, from flight bookings and baggage inquiries to reservation changes and general travel information.
Most of the types of inquiries or tasks the virtual agent should be able to handle, such as flight bookings, reservation changes, baggage information, or general travel inquiries are identified and combined with the AWS provided Generative Ai model Bedrock.
Amazon multiple generative AI services and capabilities
Amazon Bedrock is a new service for building and scaling generative AI applications, which are applications that can generate text, images, audio, and synthetic data in response to prompts. Amazon Bedrock gives customers easy access to foundation models (FMs) — those ultra-large ML models that generative AI relies on from the top AI start-up model providers, including AI21, Anthropic, and Stability AI, and exclusive access to the Titan family of foundation models developed by AWS.
Amazon Generative AI provides two EC2 instances choice for training the models. Amazon EC2 Inf2 instances powered by AWS Inferentia2 chips, which add a cost-effective solution for running generative AI workloads. New EC2 Trn1n instances powered by AWS Trainium chips are available to train generative AI models faster.
CodeWhisperer, Amazon’s AI-powered code-generating service tool is available free of charge for developers. CodeWhisperer supports Python, Java, JavaScript, TypeScript, C#, and many other languages, and it can be accessed within the AWS Lambda Console, Visual Studio Code, and other IDEs.
Amazon Bedrock
Amazon Bedrock is an innovative service designed to facilitate the development and scalability of generative AI applications. These applications have the remarkable ability to generate text, images, audio, and synthetic data in response to prompts. With Amazon Bedrock, customers gain convenient access to foundation models (FMs) — the powerful, ultra-large machine learning models that are at the core of generative AI. These foundation models are sourced from top AI start-up providers such as AI21, Anthropic, and Stability AI, along with exclusive access to AWS’s own Titan family of foundation models.
Recognizing that no single model can excel in every aspect, Amazon Bedrock presents a diverse range of foundation models from leading providers. This empowers airlines with the flexibility and choice to select the most suitable models for their specific needs. Whether it’s generating coherent text, producing stunning images, composing realistic audio, or creating synthetic data, Amazon Bedrock ensures that customers can leverage the best-in-class models to achieve optimal results.
By leveraging foundation models from top AI start-ups, Amazon Bedrock enables customers to tap into the cutting-edge advancements in generative AI.
Furthermore, the exclusive Titan family of foundation models, developed by AWS, serves as a valuable addition to Amazon Bedrock’s offerings. These models have been carefully engineered and fine-tuned to deliver exceptional performance, reliability, and scalability on the AWS platform. With Titan models, customers can harness the full potential of generative AI, leveraging the strength of AWS’s infrastructure and expertise.
Amazon Bedrock goes beyond providing foundation models; it offers an ecosystem that supports the entire lifecycle of generative AI applications. From development and training to deployment and scaling, Airlines can rely on Amazon Bedrock to simplify and streamline their AI workflows. The service integrates seamlessly with existing AWS tools and services, enabling airlines to leverage their familiar infrastructure and take advantage of AWS’s comprehensive suite of AI offerings.
Post implementation Scenerio
As the airline implemented the generative AI models, they witnessed an incredible transformation in customer experiences. Customers were amazed at how the virtual agents engaged in meaningful, context-aware conversations. The virtual agents could understand the intent behind customer queries and provide accurate and personalized responses, surpassing the customers’ expectations.
One particular customer, Shweta had an unforgettable experience. She called the airline’s contact center to inquire about a flight change due to an unexpected event. As she spoke to the virtual agent, she was surprised by the agent’s empathetic tone and understanding of her situation. The virtual agent not only processed her request promptly but also suggested alternative flight options that suited her preferences. Shweta was delighted by the personalized support she received, which turned a potentially stressful situation into a positive interaction.
Behind the scene
The airline’s contact center team constantly monitored customer sentiment using Amazon Comprehend’s sentiment analysis. This allowed them to gauge customer satisfaction levels and identify areas for improvement. The generative AI models were continuously trained and refined based on customer feedback and sentiment analysis results. This iterative process ensured that the virtual agents became increasingly effective in understanding customer needs and delivering exceptional experiences.
AWS offers a variety of generative AI services, including:
- Amazon Bedrock is a managed service that provides a foundation for building and deploying generative AI models. It includes a pre-trained language model, a set of tools for developing and deploying models, and a managed infrastructure for running models.
- Amazon SageMaker JumpStart is a collection of pre-trained generative AI models that you can use to build applications without having to train your own models. The models cover a variety of domains, including text generation, image generation, and music generation.
- Amazon Lex is a service that helps you build conversational AI applications. It includes a pre-trained language model that can be used to generate natural language responses to user queries.
- Amazon Transcribe is a service that helps to recognise speech and converts into text.
- Amazon Polly is a service that converts text into speech. It includes a variety of voices that you can use to generate different types of audio content.
- Amazon Rekognition is a service that can be used to detect and analyze objects, people, and text in images and videos. It can also be used to generate synthetic images and videos
- Amazon Translate service will be used to translate between languages.
The models were trained quickly with less expense, ultimately leading to more services powered by generative AI models.
Word quickly spread about the airline’s revamped contact center and the innovative use of AWS and generative AI. Customers began to choose this airline not only for their excellent service but also for the personalized and efficient support they provided throughout the customer journey.
Conclusion
Integrating AWS Contact Center and generative AI into their existing contact center proves to be a game-changer for any airlines. The combination of intelligent virtual agents, personalized interactions and continuous improvement transformed customer experiences. Through this visionary approach, the airline can elevate customer support to new heights, establishing a reputation for exceptional service and cement their position as a leader in the industry.
