Inspiration One of our team members frequently struggled with managing short-term tasks efficiently. Instead of making progress, she found herself cycling through tasks without accomplishing meaningful work. This challenge inspired us to develop a solution that optimizes task management and time allocation.
What It Does CALI takes your schedule and task list and automates time allocation, ensuring you focus on the right tasks at the right time. It provides personalized recommendations on what to work on and for how long during your available free time.
How We Built It We developed CALI using React for the frontend and integrated the FullCalendar API for scheduling functionalities. The backend was implemented using JavaScript, Node.js, and OpenAI's API to enhance task automation and intelligence. Through the use of structured queries and chain-of-thought reasoning, our chosen model was able to effectively interpret and construct schedules that best fit user needs.
Challenges We Ran Into One of the primary challenges we faced was efficiently passing information between the frontend and backend, ensuring seamless communication and data processing. In addition, integrating the OpenAI API presented its own set of difficulties. Much of our effort was dedicated to thoroughly reading and understanding the documentation as well as configuring the environment to get the API calls working correctly. This process required careful debugging and experimentation, adding complexity to our development workflow.
Accomplishments That We're Proud Of We successfully implemented API calls and even built a custom API using the Express library to bridge the frontend and backend, allowing smooth data flow and interaction. Our ability to quickly adapt to new tools, pivoting our approach as we faced numerous difficulties, allowed us to strengthen our communication skills and teamwork abilities.
What We Learned Throughout this project, we gained valuable experience working with OpenAI’s APIs and enhancing our skills in API integration and backend development.
What's Next for CALI We plan to scale CALI by introducing features that support long-term goal planning and a built-in learning assistant. This would enable the AI to suggest additional tasks based on users’ long-term objectives. For example, if a user aims to learn a new language, CALI could recommend relevant resources and structured activities to aid in the learning process. We aim to make our own machine learning model, using data from real life users. This would allow us to tailor the model more precisely, and assist users in making practical decisions.
Log in or sign up for Devpost to join the conversation.