NoteKan

About NoteKan

NoteKan was born out of our team's desire to streamline the Agile planning process and make it more accessible to teams of all sizes. We were inspired by the need for a tool that could quickly capture ideas and requirements, while also providing a structured framework for turning those ideas into actionable plans.

What Inspired Us

As developers ourselves, we know firsthand the challenges of managing Agile projects. We often found ourselves spending more time on administrative tasks like creating Kanban boards and writing requirements documents than actually coding. We wanted to find a way to automate these repetitive tasks and free up more time for the work we love. We were also inspired by the growing popularity of voice-powered assistants like Alexa and Siri. We saw the potential for voice dictation to streamline the planning process even further, allowing users to capture ideas on the go without having to type.

What We Learned

Throughout the development process, we learned a lot about the challenges of building an AI-powered application. We had to grapple with issues like natural language processing, speech recognition, and machine learning. We also had to figure out how to integrate these technologies seamlessly with our application's user interface and backend systems. We also learned a lot about the importance of user experience and design. We spent a lot of time thinking about how to make our application intuitive and easy to use, even for users who might not be familiar with Agile methodologies or AI technology.

How We Built It

We built NoteKan using a combination of open-source and proprietary technologies. For the speech recognition and natural language processing components, we used OpenAI's Whisper speech-to-text API. We also used OpenAI's GPT-4 language model to generate the requirements documents based on the user's voice recordings and chosen template. For the backend, we used Next.js to handle the API requests and manage the data flow between the different components. We used Google's Firebase to store the user's voice recordings, templates, and generated documents. For the frontend, we used Node.js and tailwind to create a modern, responsive user interface. We also thought to use WebSockets with Express.js however the WebSockets were much more difficult to manage.

Challenges We Faced

One of the biggest challenges we faced was integrating all of the different technologies and components into a cohesive, working system. We had to figure out how to pass data between the speech recognition, natural language processing, and document generation components, and how to handle errors and edge cases. We also faced challenges with finding the right tech stack for us. We started with Google Cloud speech-to-text and then chose to switch over to whisper due to cost and integrability. Finally, we faced challenges with scalability and performance. We also used WebSockets and an expressjs server, to begin with, but quickly found out the difficulties and incompatibilities with express and react, so we switched to using the nextjs server functions. Overall, we struggled through choices, but out ability to take a step back and find the best technologies for our product allowed it to be one of the most amazing experiences.

As more users start using NoteKan, we'll need to ensure that our system can handle the increased load without sacrificing speed or reliability.

Conclusion

Despite these challenges, we're proud of what we've accomplished with NoteKan. We believe that our application has the potential to revolutionize the way teams plan and collaborate, and we're excited to see what the future holds. If you'd like to learn more about NoteKan or try it out for yourself, please visit our website at https://notekan.com/. We'd love to hear your feedback and ideas for how we can make NoteKan even better.