Pro bono law firms often serve clients who are systematically marginalized or in dire need without means for help. Additionally, these lawyers have limited resources to assist these cases. We are changing that through our JustinCase. We are able to create a community of pro bono lawyers - connecting them with each other and providing a simple way to search decades of cases in order to create stronger arguments.

What it does

JustinCase utilizes law APIs to simplify access and search of previous law cases, arguments, and results. It is a web platform with a built in AWS chatbot that utilizes numerous legal APIs to effectively search previous cases based on a number of descriptors. With a user dashboard, it allows the user to keep track of the case at hand and compare it to other cases on the database, classified by both recency and court level.

How we built it

We built the core chatbot on AWS Lex, and made it more intelligent through lambda functions with python. The front end of the website was built using HTML/CSS and Javascript. The chatbot is sever-less as it uses AWS backend and incorporates APIs directly to the chatbot. For the user dashboard and main website backbone, we utilized Google App Cloud to host our server and allow the user's information to be stored for more functionality and convenience.

Challenges we ran into

Throughout the making of the backend, we found it challenging to incorporate the API into the website because of many incompatibilities between Python 2 and the request modules needed to access information from APIs. Furthermore, we spent a lot of time researching how to use the AWS Lex chatbot and how to debug on it. However, we were able to resolve these by implementing creative solutions to overcome incompatibilities and bugs.

Accomplishments that we're proud of

As we made our project, we were able to gain familiarity quickly with the new technologies we used, from Google App Cloud to chatbots. We're proud of how much we improved in debugging and that we were able to reach a functional minimal viable product that can make a positive impact on our users.

What we learned

While making JustinCase, we learned a lot about the integration of different services and how all these technologies can be leveraged together most efficiently. We also learned the importance of planning beforehand to ensure that we have a minimal viable product and that we are delegating tasks according to our strengths and weaknesses as team members. By working together on JustinCase, we bonded as a team and have been inspired to continue using these technologies to make a positive impact on the world around us.

What's next for JustinCase

While we reached our core goal with JustinCase, we have a lot of room for added functionality and efficiency. We are planning to continue expanding it to include neural networks that streamline the chatbot service and provide cutting-edge guidance to lawyers utilizing database information for them to find more relevant data, form stronger arguments, and provide better defense for the clients who need it the most.

Built With

Share this project: