Parasol Insurance AI Workshop Parasol Insurance lab Overview This lab will illustrate how the use of various AI/ML technologies can be combined to produce a valuable solution to a business problem. The information, code, models and techniques it contains are illustrations of what an AI-enhanced application first prototype could look like. It is not the definitive way of addressing the stated requirements. Disclaimer This lab is an example of what a customer could build using Red Hat OpenShift AI. Red Hat OpenShift AI itself has no specific feature related to Insurance Claim Processing. This lab makes use of large language models (LLM) and image processing models. These models are not included in the Red Hat OpenShift AI product. They are provided as a convenience for this lab. The quality of these models is enough for a prototype. Choosing the right model to use in a production environment is a complex task that requires a lot of experimentation and tuning. This lab does not cover this aspect. Timetable This is a tentative timetable for the materials that will be presented. Name Duration Type Description Background 5 Presentation We describe what the desired end state looks like. Describe overall user experience and underlying architecture. Share mockups for better visualization Connection and Setup 5 Hands-On Attendees get connected help validate environment health access the playpen project LLM 20 Hands-On summarization check sentiment check Model Comparison check and choice prompt engineering exercise confidence-check pipeline Image Processing 20 Hands-On car recognition checks re-training exercise model deployment Web App 20 Hands-On deployment update RAG Productization 5 Presentation + discussion What else could we add that would have value? What else could we do following the same patterns? Contributing If you are interested in contributing to this project, consult this GitHub Repo: https://github.com/rh-aiservices-bu/parasol-insurance/ 1.1 Setting the stage