Anubhav Mishra

To gain trust in Generative AI applications, a robust observability framework is needed. In this session, we will demonstrate how users can instrument an AI application with Trulens, an open source observability framework, to trace each component of their application and use LLM-as-a-Judge evaluations to identify and improve points of failure. Attendees will learn about best practices in enabling observability in their AI workflows and common feedback functions used for evaluation. We will also explore using the observability framework as a mechanism to compare application versions to determine which version is best fit for production use.

Delighting their customers with quick and easy responses remains central to the customer experience strategy for support organizations. In this chalk talk, learn how generative AI can help you efficiently use curated content to respond appropriately to FAQs.

Customers calling in for support expect personalized experience and a quick resolution to their issue. With chatbots, you can provide automated and human-like conversational experiences for your customers.

This session covers a new integration between Amazon QuickSight and Amazon SageMaker that makes it easy to connect to and use your predictive analytics models from Amazon SageMaker with Amazon QuickSight dashboards and analyses. Please bring your laptop.

In this chalk talk, we discuss how to build an Amazon Lex chatbot that can conduct a conversation based on data in a sample business intelligence database. We then explore ways that this chatbot could be adapted to your own datasets.