
CACI Helps U.S. Navy Reserve Increase Readiness with Mobile Q&A Chatbot Built on AWS
Learn How CACI collaborated with the U.S. Navy Reserve to give reservists fast access to critical documents.
Benefits
56,000+
reservists helped to find data faster4 months
to create and deploy a Q&A chatbot in productionReducing
the need for support callsOverview
The mission of the United States Navy Reserve is to provide strategic depth and deliver operational capabilities to the Navy and Marine Corps team and Joint forces in times of peace or war. Warfighting readiness is the top priority for the Navy Reserve and is achieved through continuous training of Reservists in their wartime roles; by constantly improving mass-mobilization processes and procedures; and by ensuring the timely dissemination of accurate information. In support of this mission, the Navy Reserve turned its focus to generative AI technologies and worked with AWS Partner CACI to build a mobile Q&A chatbot to provide Reservists with greater access to, and targeted search capabilities within, important policies and guidelines.
In concert with AWS, CACI built the Navy Reserve's chatbot in four months, relying on AWS services including Amazon Kendra and Amazon SageMaker to reduce development time. The chatbot aids Reservists in accessing critical information quickly and more easily empowering them and reducing the need for support calls to their command.

About AWS Partner CACI
CACI is an AWS Partner that delivers expertise and technology to U.S. government customers to strengthen national security.
Solution | Creating and deploying a Q&A chatbot in four months on AWS
CNRFC N65 decided to work with CACI, an AWS Partner, to turn RAIN into a mobile Q&A chatbot application. CACI, which provides solutions and services for federal government agencies, has developed and maintained business systems for the Navy Reserve for more than a decade. Tasked with developing a new solution, CACI leveraged its Strategic Collaboration Agreement (SCA) with Amazon Web Services (AWS) for assistance getting started. An AWS SCA is a strategic agreement that fosters a closer working relationship between AWS and a customer or partner, enabling them to leverage each other's strengths and expertise to achieve shared goals and drive innovation in the cloud computing space. “CACI is leaning heavily into generative AI technology, and we are familiar with the expertise AWS has in AI technologies through our relationship,” says R. J. Lewis, Software Engineering Lead at CACI. Supporting CACI via the SCA, AWS Senior Solutions Architect Dave Horne quickly grasped the problem and expertly guided CACI through an evaluation of relevant AWS services and solutions. One of those solutions is QnABot on AWS, a ready-to-deploy multi-channel and multi-language chatbot that integrates with Amazon Kendra, an intelligent enterprise search service.
CACI used Amazon Kendra to incorporate semantic search capabilities into a Retrieval-Augmented Generation (RAG) workflow within the new app. “QnABot on AWS gave us a lot of what we needed, and we liked the integration with Amazon Kendra,” says Jared Shields, Technical Lead at CACI. “We used some core tenets of the QnABot architecture, and then we carried forward those capabilities and knowledge into building our own chatbot solution.” CACI implemented the chatbot in AWS GovCloud (US), which is designed to enable government agencies to host sensitive workloads. “Although we do not currently process Controlled Unclassified Information (CUI) with our solution, we built within AWS GovCloud to ensure we’re ready when the time came,” Shields says.
To accelerate development, CACI developers used Amazon SageMaker deep learning containers with an embedded text generation interface and AWS Lambda to run code in a serverless compute environment. “Amazon Kendra helped us speed up development of our RAG pipeline because it simplified document ingestion and made it easier for us to perform semantic searching against unstructured documents,” says Shields. “Similarly, Amazon SageMaker made it easy for us to get an LLM up and running in a few hours, a task that would have taken us significantly longer without the real-time inference services provided by Amazon SageMaker. By relying on services like Amazon Kendra and Amazon SageMaker, we were able to create and deploy the application in about four months.”
Outcome | Increasing readiness by helping reservists access critical documents quickly and easily
Every day, more than 8,000 Reservists use the new Q&A chatbot to get instant mobile access to Navy Reserve directives and instructions that are authorized for public dissemination. Now, instead of spending time searching for the organizational processes and procedures they need, Reservists can find this information faster through reliable prescriptive and generative responses. The Navy Reserve expects the application to reduce the need for support calls to command support staff who would typically have to manage information requests and disseminate documents to Reservists. “This application is increasing efficiency for the Navy Reserve,” says Stewart. “Eventually, the app could create fitness reports and appraisal documents from a series of bullet points and return that information quickly.” Ultimately, the Navy Reserve anticipates it will increase readiness for Reservists by streamlining information through the chatbot. “The Q&A chatbot on AWS helps our Reservists be more prepared by giving them all the data they need at their fingertips,” says Stewart.
The Navy Reserve is working with CACI to build additional solutions on top of AWS services such as Amazon QuickSight. “CACI receives frequent requests to build new capabilities for the Navy Reserve,” Shields says. “Now that we've experienced leveraging AWS services beyond solely infrastructure as a service, we're finding significant value in terms of speed of development and cost. The SCA CACI has with AWS will help us continue to help our customers accelerate cloud migration, integrate artificial intelligence technologies, and achieve outcomes faster.”

The Q&A chatbot on AWS helps our Reservists be more prepared by giving them all the data they need at their fingertips.
Joel Stewart
CNRFC N65 Division Director, United States Navy ReserveAWS Services Used
Did you find what you were looking for today?
Let us know so we can improve the quality of the content on our pages