Read With Me: United Airlines uses Amazon Bedrock to innovate technology for customers

(Illustration: Lac de Neuchatel, Switzerland. Image source: Ernest)

United Airlines recognizes the significant potential of generative AI to drive value across its business operations, from improving customer experience to increasing operational efficiencies. However, they also understood the risks and pitfalls associated with this emerging technology. In partnership with AWS and their Amazon Bedrock generative AI service, United developed a strategic framework to responsibly implement and scale generative AI use cases. Their approach focused on innovation propelled by inclusion, rapidly prototyping high-value low-complexity use cases first, and building on their existing (15-year) MLOps platform and data engineering capabilities. United sees Bedrock as key to unlocking generative AI’s potential through its fully managed service, API framework, choice of models, and data security. Looking ahead, their priorities include enhancing prompt engineering, multimodal models, cost optimization, and fine-tuning models for specific use cases.

tl;dr

United partnered with AWS Amazon Bedrock to strategically adopt generative AI across its business
Their approach focused on rapid prototyping of high-value, low-complexity use cases first
Use cases centered on improving customer experience through summarization, conversation, sentiment analysis
Priorities include responsible AI, model choice/customization, and generating business value
Future areas of focus include multimodal models, cost optimization, and model fine-tuning

Watch the Video

Content selected from AWS Events. Full session please refer to AWS re:Invent 2023 - Accelerate generative AI application development with Amazon Bedrock (AIM337).

Content

United Airlines ML Engineering

I’m Sanjay Nair. I’m from United Airlines. I head up our Data, AI, and Analytics Engineering. I’m the part that gets you out from the generative AI created Octank Bank scenario to the real world customer perspective from one of the largest airlines in the world. To build on the story, the product, the technology that Mark and Girish walked you through with Amazon Bedrock, I’ll start with a quick introduction of the team, talk about the challenge and the opportunity that presented itself this year, talk about how we strategized, designed, and implemented our solution in partnership with strategic partners like AWS, and then talk about the path forward: how we think we can unlock the vast potential of generative AI using Bedrock.
Our mission at United Airlines is to be the best airline in aviation and what that means is more than just being the best airline in terms of size or our route network, in the number of destinations we fly to, or even the number of customers we carry. But it’s to be the best in driving the best customer experience for our customers, in driving the highest customer loyalty, and engendering an engaged employee workforce.
What’s really exciting about our story is the growth strategy, which entails adding over 700 aircraft to our fleet over the next few years—that’s almost doubling our fleet—but doing it in a way that we’ve called our motto: “Good leads the way.” It’s about doing it in a way that does good for the communities that we are privileged to serve and doing right by the customers that we carry on our aircraft.
Now, we are a complex business, and we believe at United that AI and ML, and in particular generative AI, is going to have significant incremental value to our business and the many different domains of our business, whether it’s network operations, inflight or flight operations, revenue management, the commercial side of the business, or tech ops in maintenance. And we have my team, which is privileged to support the entire enterprise, whether it’s in operations, commercial, digital, and beyond, to implement the platforms on generative AI that we believe will add significant value.

The Gen AI opportunity

I think it would be a safe bet to say that when 2023 dawned, most of our companies here did not have a plan for generative AI; it was more that generative AI hit us than we had a plan for it. But we had to react quickly, all of us, and the reason we at United had to react quickly was a lot of our vendors, a lot of our partners, were reaching out to business users across the enterprise with solutions that are going to solve all their problems.
But while we recognized the vast opportunity that existed with generative AI, we also recognized the risks and the pitfalls of this technology.
Number one, of course, it’s new. But of course, we also knew that there are risks with it. But what we set up was a set of guiding principles that helped us strategize for this program. The first, of course, is we’re going to listen to all of our business users and all the ideas that we have that we call innovation propelled by inclusion, so we want to make sure we considered all the use cases and we had the right approach to select which ones made sense for generative AI. And of course, we had to get them to market quickly because that’s where all these different use case and partners were coming in with saying they can implement these things quickly. So that was a prime consideration for us. And of course, thirdly, we had to have an easy and quick integration because that was also being promised by other partners and vendors.
So what did we do? We got a few of our strategic partners together, and AWS, of course, is our strategic partner that we've been using for our modernization of our digital technology platforms to the cloud and to help us separate hype from reality.

Amazon Bedrock solution

And that’s where we got introduced to Bedrock as one of the first companies to preview it. And the few of the features that really convinced us about Bedrock was the fact first, it’s a fully managed AWS service which is great because it’s built on the existing AWS platform that we have and second, it works with, like Girish mentioned, an API invocation framework that makes it really easy for our business users and our application development partners to use it. And third, and most importantly, it provided the choice of models that we really needed because we all knew and know this is still an emerging world; there are a lot of things we don’t know about this program, if you will. So we wanted to have a choice that we could experiment with, play around with, and then decide what was the most optimum model that worked for a use case.
On top of that, of course, we didn’t want to have these point solutions all over the enterprise that would make security a nightmare, it would make responsible AI a nightmare. And so we wanted to make sure that we have centralized operations to enable us to drive this whole body of work forward. I talked about security already—security matters for large enterprises—and so this was critical for us to make sure that Bedrock has a lot of features and capabilities that comes with the implementation, the platform that was important for us to make this selection.
And I talked about experimentation and quick prototyping—that’s where you decide whether the use case is good or if it not, then we have the platform for failing quickly and moving on to the next use case, which brings us to where if this use case makes sense, how do we scale it and get ready for production? That really is the strength of AWS, which provides the platform for us to scale these use cases to production quickly.
So let’s talk about a little bit about the technical architecture that we built this from now. AI and ML are not new to United; we've had ML for almost 15 years, but what's really exciting was the last 15 months that we built our MLOps platform on top of our United Data Hub or our data platform that we modernized on the cloud, and that really was the platform that enabled us to accelerate and implement generative AI for United.
And that’s the platform that we integrated Bedrock with, in partnership with AWS. With all of the solution architects, and partners that we have, we were able to create the platform with Bedrock bolted on top of our MLOps platform, and that gave us those capabilities we talked about previously: the API invocation, the multiple choice of LLM models, and then from there we could extend Bedrock and our MLOps platform into other things, like what Girish talked about in terms of the knowledge base and the vector database that would help us with embedding documents and document chunking that would preserve the context and the memory for the prompts and the responses, and for continuing conversations of these LLM models.
And of course, we would extend this further as we implement the API framework into things like service logging, to log the prompts and the responses, to make sure that we are able to store it in our S3, in our United Data Hub, and then we can use it to further improve and fine-tune our models going forward. We also added some accelerators and adapters to this framework which is, CS templates here, and these templates are things like for summarization which, again, G talked about as well as chatbot templates, and these really helped our use cases and our business users. This will continue to pay forward as more and more use cases come, these templates can be used to accelerate the implementation and, more importantly, reduce the customer work that our business users and application development partners would need to use.
Most importantly, no discussion on a technical architecture for generative AI can be complete without a responsible AI conversation as well, especially for companies of our size. A lot of these functions come built with Bedrock and a lot of these things we are extending as well, with things like response filters and context filters to make sure that we are monitoring things like tonality and toxic responses potentially that we can then work and tune out as we put a human in the loop as we work these use cases forward.
But really the key takeaway from this slide really is that AWS and Bedrock provide the foundational infrastructure, and they’ll continue to innovate and support that, and what we believe we’ll focus on is the data to create the data knowledge base and then focus on the prompts and the responses to continue to generate value, significant value for the business.
So let’s talk about some of the learnings over the past few months based on what we talked about in terms of the technology and the framework. First, really that was helpful to us was we didn’t have to pivot our data and ML engineering team 180°; we were able to build and grow from the base that we had built on our AWS MLOps platform, and that really was a validation as well as a great accelerator for our engineers and my team especially, to be able to deliver these solutions to market quickly.
Secondly, was really to build the organization and the communication framework because to support an enterprise of our scale and magnitude, we needed to make sure that we are getting the message about not just the strength of generative AI in Bedrock, but also about the potential risks and how do you manage the responsible AI components, and how do we manage the risk associated with it.
So that really set us up to be able to grow these use cases and proof of concepts with the right framework to support it. So if I was to summarize the learnings, in a sense, there are three chapters to this book. First, is to create the program structure that provides the framework to intake these use cases and proof of concepts, and then evaluate their readiness. And the second chapter really is around the readiness itself to make sure that you have a framework by which, what we used was a matrix with value on one of the axes, complexity on the other, and really started focusing on the ones that have high value and low complexity to start with. And that provided the experience for us then to go towards the more complex use cases that would yield high value as well.
So, what were some of the use cases? So we focused really on our customer, and we talked about the employee base and a lot of our employees who are now joining the company to support our growth are from a demography that loves technology, that’s grown up digitally native, loves to use generative AI really. And so that we feel was a perfect fit for us to enable them to be able to support the customer better, optimize communications to the customer and, more importantly, with generative AI, understand the customer sentiment, understand customer satisfaction, and drive actionable insights from that. So we put the customer at the center of these use cases as we develop them.
Building out what Girish had said, I would summarize by saying we had four or five categories of use cases models.
The first was around summarization and rewriting; we have a lot of complex policies, business rules, and generative AI can be particularly useful in summarizing and bringing the relevant portions of that information, policy, and business rules for the employee and the team member to be able to present to the customer. That we feel is going to bring significant value.
Second is around the conversational, the chatbot type use cases that's more interactive one-on-one with the customer; again, we feel there’s a lot of value for generative AI to summarize and bring the information back to enable this one-on-one conversation, whether it’s by an agent or with our digital tools, including our award-winning United Mobile app, that really can use this technology to provide a lot of value to the customer and the employee.
Third is around sentiment analysis, like I mentioned, we have vast rows of customer feedback that come in, and use this knowledgebase, use our platforms to be able to glean from there real actionable insights that’ll drive forward more projects and more initiatives that can improve customer satisfaction and customer experience.
And the fourth is around really the more emerging area of multimodal LLMs, if you will, and that’s where things like text to speech and speech to text, and really a summary of all the other use cases that I mentioned can provide a more immersive experience, whether it’s the customers or our employees, to be able to improve customer experience. And that’s an exciting frontier, if you will, as we see going forward.

Unlocking business potential

Um, in this space, now, now let’s talk a little bit about how we believe Bedrock can enable these use cases to be brought to life and gain fruition.
V and the first team really, and the recurrent theme, in a sense, is for us around responsible AI and security, right? And a lot of this is what Girish had mentioned as well, the trust and the belief that our data will not be used to train foundational models. Our data is ours and that’s really key for us to be able to have the peace of mind that it’s not going to be used for other purposes.
Second, of course, is to enable the democratization of generative AI, and we believe with Bedrock, with the choice of the models that it provides, it will really help to get AI spread across the enterprise which is key to delivering the business value.
Third is around business efficiency, we believe that there are, as we modernize our, our way, uh, to the cloud, a lot of our legacy platforms, software can be transformed using generative AI, and we believe big area of value as well going forward.
And last but I think most important, what really Bedrock provides is this model choice and customization, and that’s where we don’t yet know what we don’t know, and so have this choice at our hands to be able to experiment, play with it, and continuously improve the output coming back from these LLMs is going to be key in the intermediate and the long term to generate value for United.
So now let’s bring this back to where we had started with in terms of where this is going, what’s our path forward, how do we think this innovation will work? And the key theme again is, we using Bedrock and partnering with AWS because we believe that they will continue to innovate with Bedrock, and then we can focus on how do we generate value with the data that we have and the use cases that we will create and ideate upon. But there are three categories that I want to talk to here.
First, of course, is again the recurrent three around responsible AI and security, and we’re putting the right guard rails in place to be safe and keep our customers and employees safe as well. And we’re working on things like prompt engineering now. Girish talked about retrieval augmented generation, that’s going to be a key focus for us as well, to how we add incremental content and knowledge bases to the data from foundation models to make sure it’s providing responses and we can fine-tune these models for our specific purpose and value.
The second is around the platform, and this is really where the optimization needs to happen. Through this presentation, you haven’t heard a lot about cost, but that’s going to be a big important consideration for any company including ours, and so cost optimization is going to be a key component as we look forward, and how that happens as these tens and hundreds of use cases come to market, we’ll have to manage this cost, and we believe that having that top of mind is going to be important as we go forward. So things like hardware optimizations, having the right chips for the right use case as well as the database optimizations is going to be important for us going forward in terms of also model monitoring as well as carrying out these tests to make sure and evaluations to make sure that this is generating the value that we think we had envisaged.
Lastly, and equally important as any, is the models themselves, right? And we talked about the choice that Bedrock provides in terms of customer models and more that will come in the times going forward. So we are particularly interested and excited about this multimodal opportunity as well, and then also working towards fine-tuning some of our the models here for United, trained and specific use cases that will also help us optimize the cost going forward, that we don’t have to use larger trained models that are out there as well.
So that’s those are the areas that we’ll be looking to going forward, um, in the near future. Again, bringing this to close, our focus is going to be on our use cases, on our data while we partner with AWS on enhancing and working towards a more innovative Bedrock platform so that our data engineers and our ML engineers can focus on partnering with our businesses to make sure that we create business efficiency and, more importantly, create the customer experiences that enable our customers to keep coming back and flying on United Airlines. That’s our story, thank you. And with that, I’ll hand it back to Mark.

Reference

Loading comments…