Inspiration
We believe that the technology and data-driven decision-making going on at an enterprise level for large companies like Google, Netflix, Walmart, and others can trickle down to smaller business levels. Currently, many small-sized to mid-sized business owners struggle to use data effectively in their operations. We wanted to change that, and thought that Gemini could play a critical role. This was our inspiration for Butler.
What it does
Butler is a personal data analyst who makes the data synthesis process simple and quick for business owners or leaders, even if they don't have a technical background. Data visualization tools like Tableau are too difficult to set up; for business owners who are beginning their data-literacy journeys, we wanted to create a tool that utilizes Gemini's data-surfing and data-summarizing capabilities to not only convey insights for the user through text, but also visualization. Butler utilizes a complex Python code structure surrounding the Gemini API to allow Gemini to take background information about the user, their role, and their industry, along with a dataset, and generate a custom view for the user. Gemini not only decides the layout of the visualization but also the x and y axes for visualizations like line and bar graphs.
How we built it
We used a Python library called Streamlit, which is great for Proof-of-concept projects to set up a Python architecture. Connecting to the basic Gemini API, we retrieved key words from our prompts to the model and used those key words to set in motion a series of Python functions to create dynamic visualizations for the user.
Challenges we ran into
This process was not easy. Overall, our largest obstacle was time. With Aubrey moving across the country, and Jacob starting a new job and graduating from college, finding the time to develop a robust structure wasn't easy. But we are glad we did it!
Accomplishments that we're proud of
We are proud that we created a platform that enables small business owners to take control of their data. We are proud of our teamwork together despite moving across the country and full-time jobs. We are proud to bring our minds together for a project as awesome as this!
What we learned
We learned that Gemini is an extremely powerful API. We learned that we literally have the ability to change the world and that AI is a good thing, not a bad thing for the future of society. We also learned that creating a product is difficult, but worth it when we can see real actionable impact on people around us.
What's next for Project Social
The next implementations we have include adding the ability for users to export individual visualizations, live integrations with the cloud, added file types, and more.
Log in or sign up for Devpost to join the conversation.