Project Brief: Ultimate Rules



I got my law degree from Georgetown University and I have an interest in exploring topics at the intersection of law and technology. I’m also an avid Ultimate Frisbee player. I noticed that the Ultimate rule book is structured much like a complex legal document (I guess it is one). In any given game situation it’s too cumbersome to use the rule book to find the applicable rule. So I wanted to see if I could use my skills as a developer to solve that. The hope is that a solution where might also apply in other more important areas where complex legal rules have to be navigated quickly.


I decided to make an iOS app where the rules were tagged according to topic. Each rule has one or more tags applied to it and any related or cross-referenced rules are also easily accessible. I really like the app and it has been super-useful when there has been a dispute about rules because the relevant rule can be located in around 2 sec. Right now, I am beta-testing the app via TestFlight, while I fine-tune functionality and make sure I’m getting the right analytics.

It took a long time to go through the 365 rules of Ultimate and tag them by topic. In the end I had 80 topics for tagging. There are different rules for the different professional Ultimate leagues (AUDL, MLU). An experiment I’m doing is to see if I can use machine learning to automatically tag the other rule systems using this data as a training set. I’m also experimenting with making the app responsive to voice queries. In the legal context, I think it would be interesting to apply this to something like the Federal Rules of Evidence – another system of complex rules that need to be referenced quickly.

Technologies and Methods