Hi there. Is there an efficient way to run A/B test for increasing retention? I see there is an option to set up a metric of the "duration" type but it's not quite the same

It depends on how you define retention. I've seen it defined some places as the "percent of people who come back a week after being put into the experiment". In that case, it would be a binomial metric

Oh, that's right. That's something to get me started