Yeah, that makes a lot of sense. I started this from making an email list where I'm sending "lunch and learn" talks which I manually curate / write up descriptions. About half the people like that style, and half have specifically requested something more topical.

There are a bunch of great curated email newsletters around specific interests (Javascript Weekly, etc) so I'm aiming to do something similar, but more granular. So far the ML thing has been promising, but it helps to start from a pre-vetted dataset.