Train Lumo to understand the user interface
Lumo doesn't understand how to communicate through the User Interface very well. It should be trained. Lumo said that the character limit for a single response was about 4000 to 6000 characters. It should know the actual number and be able to feedback to the user that the limit was hit instead of indicating that it will try to better next time (it won't, the UI has a hard limit). When trying to get Lumo to format a list, it is like working with a teenager, it doesn't do what you want and says it will try to better next time. The problem is that it doesn't understand how the user interface interprets things like linefeed vs carriage return. If they Lumo and the UI both used a common format like Rich Text Format, it would cut the conversation requests way down.