I had thought I was in for a 40 minute talk, but ended up giving a 90 minute workshop on a Bayesian approach to linear regression. From a meta sense, this was a lot of work! I am not sure I would do another session that was this long. On the other hand, it felt great both that a lot of people came to the workshop, and that there were a lot of interesting and useful discussions about the material afterwards.
Anyways! I spent about a week after the workshop converting my notes and the slides into a series of three essays. They can be found here, and I hope they are useful.