I would find it better if he'd add something like an auto accept pull request bot, that allows you to append a single url (with validation check + rate limiting) to a file, that will be read by the url shortener + auto deploy on new master commit. That would be truly databaseless.
Well I would believe that even a `json` file or any other form of storage written to disk is considered a database, But your suggestion definitely brings it further away from an actual database!