Generative AI innovations can transform industries. Eight client teams collaborated with IBM® and AWS this spring to develop generative AI prototypes that address real-world business challenges in the general public sector, financial services, energy, healthcare, and other industries. Over several weeks, cross-functional teams comprised of client teams and IBM and AWS representatives worked to design, develop, and iterate prototypes that push the boundaries of what is feasible with generative AI.
IBM used design pondering and a user-centered approach to guide the teams through the hackathon. AWS offered enablement sessions and hands-on workshops that gave participants the mandatory knowledge and skills to make use of AWS's generative AI services, corresponding to: Amazon Bedrock And Amazon Q effectively. Pre-enablement helped teams understand AWS technologies after which put that understanding into practice. Their results will influence the following generation of business solutions that improve customer experiences, increase worker productivity, and optimize business processes.
Use case 1: Generative AI for change management
A number one financial services company faced the challenge of managing the massive volume of change management tickets and identifying potential risks related to implementing changes in production environments. The team developed a “Generative AI for Change Management” solution to enhance the standard of change management tickets and discover the likelihood of risks and defects using similar historical data.
This solution leveraged AWS services corresponding to Amazon Bedrock, AWS ECS, and Amazon Aurora to create an interactive AI interface. The interface enables change managers to create high-quality tickets and understand potential risks and areas for improvement. The solution aimed to cut back the likelihood of incidents resulting from changes made in production, improve the general change management process, and shift the main focus from ticket creation to quality improvements.
Use case 2: Intelligent feedback evaluation
An energy company wanted to higher understand customer satisfaction and discover areas for improvement based on customer feedback. The company developed an intelligent feedback analytics tool that automates the extraction and evaluation of customer comments and reviews across the energy sector.
Using AWS services corresponding to Amazon Q for Business, Amazon SageMaker, Amazon Bedrock, and Amazon QuickSight, they used generative AI to discover market trends and analyze feedback sentiment. AI was also used to categorise topics and discover potential bugs for existing features or latest feature requests from customer feedback.
The solution provided beneficial insights into the corporate's performance, key trends across the industry, and comparison with competitors, allowing key areas for improvement to be quickly identified. The data was accessible to stakeholders through a virtual assistant interface and an associated dashboard tool, providing beneficial insights into the corporate's performance.
Use case 3: Resilience through Design Advisor
A multinational bank faced the challenge of maintaining operational resilience resulting from complex technology landscapes and regulatory controls. To address these challenges, it developed a “Resilience by Design Advisor”.
This solution leveraged AWS services corresponding to Amazon Bedrock, Amazon ECS, and Amazon S3 to evaluate solution design documents and stay awake thus far with regulatory updates and industry best practices. It also integrated the bank's technology resilience framework. The Resilience by Design Advisor improved the bank's ability to discover and implement resilience measures in its applications, helping to make sure regulatory compliance and maintain high availability of customer services.
Use case 4: Analysis of citizen feedback
A government agency wanted to achieve actionable insights from citizen feedback received through its feedback service system. It used generative AI to develop an answer that would effectively analyze unstructured feedback data and extract beneficial information from it.
By using AWS services corresponding to Amazon Comprehend, Amazon Bedrock, Amazon Aurora, and Amazon DynamoDB, the answer can process text feedback and redact personally identifiable information (PII). It also identifies key topics and sentiments and generates actionable insights to enhance the service system.
Use case 5: Generative AI-powered Clinical Coding Assistant
A healthcare organization desired to streamline the clinical coding process for electronic health records. They developed a Clinical Coding Assistant solution that uses natural language processing (NLP) and generative AI to extract medical notes and convert them into standardized codes.
Using AWS services corresponding to Amazon Bedrock and Amazon Aurora, the answer could accurately process and code medical documents, reducing the effort and time spent on manual coding. This could lead to annual savings of £700,000, which could fund 20 additional nurses.
Use case 6: Self-healing CI pipeline
A government agency faced the challenge of maintaining an efficient and reliable continuous integration and delivery (CI/CD) pipeline. Manual intervention was required to diagnose and resolve pipeline issues, leading to delays, increased workloads for development teams, and potential downtime that would impact product releases. Additionally, key information for resolving pipeline issues was scattered across different documentation sources, making it difficult to access accurate and up-to-date information when needed. To overcome these challenges, the organization developed a “self-healing CI pipeline” solution.
Using AWS services corresponding to AWS Distro for Open Telemetry, AWS X-Ray, Amazon CloudWatch, Amazon DevOps Guru, and Amazon Bedrock, the answer aimed to routinely detect and resolve CI/CD pipeline errors. When a construct or deployment pipeline failed, the answer was designed to receive and process the error logs. It determines the basis reason behind the issue. It then either routinely fixes the detected issue and reruns the pipeline, or alternatively provides detailed explanations together with suggestions on the right way to fix it.
The goal of this approach was to extend troubleshooting efficiency, reduce downtime, and increase the general reliability of CI/CD pipelines. This can result in faster product releases and permit engineering resources to focus more on improving the organization's AWS estate.
IBM and AWS: Unleashing innovation
The Gen-AI Hackathon fostered innovation, collaboration and the event of breakthrough solutions. Participants gained beneficial insights into the potential of Gen-AI technologies and the way they might be used to drive digital transformation and operational excellence,” said one customer about his project, “!”
IBM, an AWS and Premier Tier Partner with the AWS Generative AI Competency, and AWS are working together to supply a platform for client teams to design and prototype revolutionary solutions that leverage the most recent AI technologies. The AWS Generative AI Competency recognizes IBM Consulting® as an AWS Partner that has demonstrated technical competency and proven customer success in helping organizations operationalize and realize value from AWS Generative AI technology. IBM and AWS are committed to reducing the barriers to AI experimentation by providing comprehensive support for pilot projects, including infrastructure credits.
Read IBM's announcement about AWS Gen AI competency certification. Learn more about IBM Consulting Services for AWS.
