Mitigating LLM Risk in Insurance: Chatbots and Data Collection
Join us for a workshop on how to evaluate and monitor production AI and LLM-powered applications for insurance use cases.
Here are the links for the workshop:
- LangKit GitHub (give us a star!): https://github.com/whylabs/langkit
Colab notebook: https://bit.ly/3x6GIlP
- Sign up for a free WhyLabs account: https://whylabs.ai/free
LLMs and AI in general have been turning heads and changing game plans across all industries. From boosting productivity to improving decision-making processes, AI systems are molding the future of business operations.
Generative AI use cases are gaining traction across the insurance sector as insurers strive to strike the right balance between harnessing value and managing risk. When it comes to exposing LLM applications to customer-facing use cases, AI builders need an exceptional level of care to meet evolving regulations and customer expectations.
Early adopters of generative AI systems are discovering that a strong evaluation and observability solution is essential to ensure uptime, reliability, performance, efficiency, and a seamless customer experience.
This hands-on workshop will work through two insurance LLM use cases:
1. Answering customer questions in a chatbot or online knowledge base setting
2. Extracting structured data from written incident reports
What we’ll cover:
Generating and evaluating text using LLMs for factual accuracy and relevance
Extracting and validating structured data from raw text using LLMs
Productionizing experimental customer-facing AI insurance applications
What you’ll need:
A free WhyLabs account (https://whylabs.ai/free)
A Google account (for saving a Google Colab)