Luckie launches an AI pilot with Amazon Q to streamline knowledge management
This marketing solutions agency tested the potential of generative AI to make its vast, dispersed knowledge base accessible to employees quickly and securely.
Industry
Media & Entertainment
Challenge
Luckie produces large volumes of data that span three disparate systems. It wanted to test drive Amazon Q Business to see if a chatbot could make information access easier and more efficient for employees.
Outcome Luckie’s AI pilot project was a success from start to finish. Rackspace delivered exactly what the firm needed to explore whether generative AI could improve employee access to its information hubs. Solutions Amazon Q Business, Rackspace Elastic Engineering, Foundry for AI by Rackspace (FAIR™) Platforms Amazon Web Services (AWS)Customer
Luckie is an insights-led marketing solutions agency that helps challenger brands turn market complexity into a competitive advantage. For more than 70 years, the agency has been building brands and brand experiences that solve real business problems, achieving results that luck can’t explain.
With offices in Atlanta and Birmingham, Luckie is one of the largest independent marketing agencies in the Southeast. The company specializes in working with companies in healthcare, travel and tourism, consumer packaged goods, and financial services. Its client partners include GlaxoSmithKline, Rivian, Alabama Tourism Department, RaceTrac, Regions Bank, among others.
“We had a longstanding partnership with Rackspace so there was already a level of trust when we started our Amazon Q Business generative AI exploration.”
Situation
Luckie has used machine learning since 2015, primarily for business intelligence modeling and analytics. But when chatbots gained traction in 2022 and generative AI took off in 2023, the company saw an opportunity to explore how these technologies could improve its internal operations. The launch of Amazon Q Business by AWS presented a unique moment to test a generative AI use case.
“We wanted to understand what these technologies could mean for Luckie — and for our marketing solutions as a whole,” said Mark Unrein, Chief AI Officer at Luckie. “We quickly recognized the need to prioritize AI and began looking for impactful use cases.”
Unrein identified an ideal efficiency use case related to the way Luckie’s internal data was distributed across multiple systems. The company generates large volumes of documentation each day — from strategic briefs and creative assets to performance reporting — and in a variety of formats, like Photoshop files, PDFs and PowerPoint decks. Employees often need quick access to the information, but doing so can be challenging because it’s spread across three platforms: Slack, AWS servers and Microsoft® SharePoint. This can make access to the most up-to-date content somewhat time-consuming.
“In my role, I’m focused on helping the organization work more efficiently so our employees can do their jobs faster, easier and better,” said Unrein. “I’m also thinking about the experience our clients have with us and how efficient we are for them. That’s why we wanted to explore the various ways AI can enhance our operations — starting with access to our vast knowledge base.”
Luckie did not have the resources or time to tackle the project alone. When the team realized that its current technology partner, Rackspace, who was already supporting its AWS infrastructure, also had deep expertise in generative AI, it chose to team up to launch its first AI pilot using Amazon Q Business.
“Overall, our mindset was to lean into our curiosity and start piloting and testing these tools,” Unrein added. “We were excited to find an existing partner that could help us. It gave us a lot of confidence to move forward with Rackspace together.”
“A differentiator for Rackspace is its long-standing strategic partnerships with companies like AWS. This showed us how forward thinking they are and demonstrated their expertise in the AI space.”
Solution
The Rackspace team had four main tasks to accomplish for Luckie’s first generative AI project. First, it needed to set up a gateway to connect the company’s Slack application with an Amazon Q chatbot. To maintain data privacy, the team used fabricated test data created specifically for this project — no production or client data was used. The chatbot was then configured to communicate with the three datasets to pull the information needed to answer employee questions and information requests.
Next, the team needed to index a subset of the data on the company’s Slack app. Then it needed to integrate the chatbot with the company’s Slack directory to install user authentication and strengthen security. The final step was installing the data into the chatbot.
The most challenging part of the process was integrating the chatbot with Slack. Instead of the usual user interface for chatbot integration, Luckie wanted its chatbot to integrate with its Slack app. The firm needed the app to talk to Amazon Q Business and pull data and documents from the Slack database. The company’s Slack app contains massive amounts of data that employees need to access on a regular and often remote basis. They also communicate back and forth and regularly share documents with each other over Slack. To make the customized connection, the Rackspace team created a custom widget.
For the pilot project, Luckie wanted to run a cross-functional test. “We wanted to test the chatbot across multiple roles and functions, involving both our junior team members and our executives,” said Unrein. “Role and department diversification in the pilot will help us ensure that everyone will benefit from the new AI tool. We also wanted to implement strong security and permissions to ensure that we had full control over who could access our data.
“Everyone from Rackspace and Amazon was incredibly helpful throughout the project,” noted Unrein. “While we have an AWS expert on staff, he was new to the processes involved in this type of implementation. He stayed in close contact with the Rackspace team — and was over the moon about their work ethic and depth of knowledge.
“From my experience during the Rackspace onboarding process, the team was fantastic — very buttoned up,” Unrein added. “Their expertise gave us real confidence. We knew we were headed in the right direction and that our data and privacy needs would be well handled.”
Outcome
“Rackspace gave us the opportunity to test drive Amazon Q Business on a very important use case, and the entire project execution was exceptional,” said Unrein. “From the early meetings to the final phase of our use case, the Rackspace team was knowledgeable, professional and efficient with tasks we could not do in-house.
“We were speaking the same language from the beginning of the project,” he added. “Our Rackspace team prompted us with key questions like: What are your use cases? Who will you use your chatbot? What do you want to get out of the tool?”
Unrein added, “To really make use of AI, you’ve got to first figure out what the utility will be. Rackspace really pushed us to pursue the best possible solution for our needs. I was particularly happy that we could apply AI to our existing platforms and knowledge bases.”
Now that Luckie has this internal AI use case test under its belt, it’s looking to expand into more use cases. For example, “we’re thinking about combining our knowledge management solution with a generative AI tool. If we could do that, we could save money because we would no longer need to pay for two services.”
Looking forward, Unrein is also eyeing the possibility of having the chatbot produce document summaries. This would make it easier for employees to access the information they need to do their jobs.
Unrein says he’ll measure the success of the firm’s AI use cases against several factors, including the ability of employees to improve the quality of their work and lower the firm’s expenses through greater efficiency.
“In the business world, we’re at the point where these tools are going to be so fundamental to the way we work. If you’re not using AI tools, everyone will be asking, ‘Why not?’”
About Rackspace Technology
Rackspace Technology is a leading end-to-end hybrid cloud and AI solutions company. We can design, build and operate our customers' cloud environments across all major technology platforms, irrespective of technology stack or deployment model. We partner with our customers at every stage of their cloud journey, enabling them to modernize applications, build new products and adopt innovative technologies.
About Foundry for AI by Rackspace (FAIR)
FAIR™ is at the forefront of global AI innovation, paving the way for businesses to accelerate the responsible adoption of AI solutions. FAIR aligns with hundreds of AI use cases across a wide range of industries while allowing for customization through the creation of a tailor-made AI strategy that’s applicable to your specific business needs. Capable of deployment on any private, hybrid or hyperscale public cloud platform, FAIR solutions empower businesses worldwide by going beyond digital transformation to unlock creativity, unleash productivity and open the door to new areas of growth for our customers.
Let’s Talk Strategy
Tell us a little about your challenges and we’ll contact you.
You may withdraw your consent to receive additional information from Rackspace Technology at any time. Information collected in this form is subject to the Rackspace Technology Privacy Notice.
Rackspace Technology Support
To create a ticket or chat with a specialist regarding your account, log into your account.
Support Phone
0800 988 0300
International Support
+1-512-361-4935
Help Documentation
System status
Rackspace Technology Careers
Rackspace Technology accelerates the value of the cloud during every phase of a customer’s digital transformation. Join us on our mission.