Inspiration
As employees, we noticed how little training and how supervisors did not have enough time to spare to answer all of our questions. So we decided that KAI would help.
What it does
It is an AI chatbot that helps answer company-related questions. It assesses prompts based on corporate data to provide accurate feedback and suggestions. In a sense, it employs the general approach of artificial intelligence. The more prompts it is given, the more accurate and expansive its responses are. Similar to a language model like GPT-3.
How we built it
KAI was built in two parts: the front end and the chatbot. The UI was created using JavaScript, CSS, and HTML while the chatbot was created using "Brain Shop", an online AI tool for developers that provides chatbot templates.
Challenges we ran into
Front-end and back-end integration was tricky. We had the chatbot functioning as well as the relevant datasets. However, we weren't able to put it all together in time.
Accomplishments that we're proud of
We were successful as a team, despite varying levels of coding expertise. We appreciate how unique and relevant our idea was pertaining to the hackathon's challenges. As we look back after submission, we're proud of our resilience to work and how eye-opening the experience was for some of us first-time hackers.
What we learned
We learned how to use and employ local-generated AI in our logo design. We also studied chatbot models and created our very own chatbot.
What's next for KAI
Our next plan of action is to integrate both ends and implement newer features for improved usability. We are confident that our project has the potential to accrue a fairly large client audience. This is due to the increasing importance and need for information retrieval.

Log in or sign up for Devpost to join the conversation.