Inspiration
We have done a lot of surveys in our lives, but all those surveys are very generic and not catered to our individual needs. We decided to change the game of feedback surveys.
What it does
Our program generates questions based on the user and his or her needs. Subsequent questions are generated based on previous responses to obtain the most significant and relevant feedback.
How we built it
We used a React front end with a Python backend and employed OpenAI to generate subsequent questions. We utilized Auth0 for a login system and Cohere's NLP to evaluate the user's responses. We also used Twilio in our multi-factor authentication system for our login.
Challenges we ran into
It was challenging to navigate between the front end (React) and the back end (NLP and Python). Additionally, we had some problems regarding database management and implementing OpenAI.
Accomplishments that we're proud of
We have a functional website that properly generates new questions based on user responses.
What we learned
Not all ideas will come to fruition; coming up with new ideas on the fly is crucial to success in this area.
What's next for CUSTOMery
Our next steps include displaying a statistical analysis of the results as a whole (what percent of people like it, common themes among people).
Log in or sign up for Devpost to join the conversation.