Inspiration
Many small business owners do not have insurance, or know how to approach purchasing insurance. Common questions include: "What policies are available to me?", "What policies are others who work in my field taking out?", "How often are claims made by others on policies that they take out?", "How can I optimize my coverage while staying inside my budget?", "What considerations should I keep in mind for my specific business?". Answers to these questions are difficult to find on the State Farm website for those who do not have the headspace to thoroughly search. The goal of our tool is to provide the customer with reference points for these questions without requiring them to take time out of their busy schedule to meet with an agent.
What it does
Our web app allows a user to communicate in natural language with a system that will assist them in deciding what small business insurance policies may apply to their range of work, their budget, and their needs. This tool provides data to the user on what policies are often taken out for their desired use case, the likelihood that others in a similar range of work have issued and succeeded in making claims on those policies (optimized to our specific user's use case), and the policies that lay within their desired budget.
How we built it
We built our project using Flask, OpenAI, and python. Our python code feeds user data from a flask managed website to OpenAI. OpenAI then communicates with our RESTful API to receive data from a JSON database. This data is then processed by OpenAI to hand the customer a natural language breakdown of their needs, their price range, and the standards for their range of work.
Accomplishments that we're proud of
We are proud of our ability to create a working product in a team with only two members that have limited experience. We also believe we have isolated a use case that truly helps the average user while maintaining State Farm's personal and approachable touch. Our tool works as proof of concept of a broader idea that simplifies the insurance world for the fast-paced small business owner.
What we learned
We learned how to use Flask to create RESTful API's, how JSON's store data and how they can be converted and used with python to create a functional web app, and how HTML, CSS, and JavaScript can be integrated with a python run Flask app.
What's next for JakePT
JakePT can be expanded to use a SQL database, allowing for more secure and detailed data access. This will allow our OpenAI model to provide the user with information more tailored to their specific situation. JakePT can also be integrated into the State Farm website, to replace the markedly less personal chat service. JakePT may also switch to OpenAI Azure models to ensure security of user data.
Log in or sign up for Devpost to join the conversation.