Principal AI Generative Experience: A User-Friendly, Secure Internal Chatbot for Faster Access to Information
Challenges, Opportunities, and Constraints
Principal, a global financial company, sought to improve the wealth and well-being of people and businesses by streamlining access to internal information. With nearly 20,000 employees and a vast amount of unstructured data, Principal required a solution that could search and analyze this data quickly and accurately.
The Solution: Principal AI Generative Experience with QnABot
Principal deployed QnABot, a multilanguage, multichannel conversational interface, integrated with Amazon Q Business and Amazon Bedrock. The solution allows employees to receive role-based answers in real-time through a conversational chatbot interface.
Implementation and Integration
Principal used QnABot’s editor to author hard-coded questions and answers. The company also integrated QnABot with Azure Active Directory for single sign-on capabilities and role-based access controls. Generative AI models hosted on Amazon Bedrock were used for query disambiguation and semantic matching for answer lookups and responses.
Usability and Continual Improvement
Principal enhanced the standard user feedback from QnABot to gain input from end-users on answer accuracy, outdated content, and relevance. The company also implemented custom monitoring dashboards in Amazon OpenSearch Service for real-time visibility into platform performance.
Results
The initial proof of concept achieved an estimated 50% reduction in time required for users to respond to client inquiries and requests for proposals. The platform has delivered strong results across several key metrics, including:
- Over 95% of queries received answers users accepted or built upon
- Over 99% of documents provided through the system were evaluated as relevant and containing up-to-date information
- 56% of total queries were addressed through either sourcing documentation related to the question or having the user attach a relevant file through the chat interface
Roadmap
The Principal AI Enablement team has an ambitious roadmap for 2024 focused on expanding the capabilities of its conversational AI platform. Future use cases are expected to use the Principal AI Generative Experience application due to its success in automating processes and empowering users with self-service insights.
Conclusion
Principal utilized QnABot on AWS paired with Amazon Q Business and Amazon Bedrock, to deliver a generative AI experience for its users, thereby reducing manual time spent on client inquiries and tasks and producing significant savings in hours and dollars. The platform effectively and quickly resolves issues by surfacing relevant information faster than manual searches, improving processes, productivity, and the customer experience.
FAQs
Q: What is QnABot?
A: QnABot is a multilanguage, multichannel conversational interface that responds to customers’ questions, answers, and feedback.
Q: What is Amazon Q Business?
A: Amazon Q Business is a generative AI-powered assistant that can answer questions, provide summaries, generate content, and securely complete tasks based on data and information in your enterprise systems.
Q: What is Amazon Bedrock?
A: Amazon Bedrock is a fully managed service that offers a choice of high-performing foundation models (FMs) from leading AI companies like AI21 Labs, Anthropic, Cohere, Meta, Mistral AI, Stability AI, and Amazon through a single API.
Q: How did Principal implement the solution?
A: Principal used QnABot’s editor to author hard-coded questions and answers and integrated QnABot with Azure Active Directory for single sign-on capabilities and role-based access controls.
