We ran a micro‑experiment: when the AI surface‑level summary includes a single user‑chosen keyword (e.g., “sustainability”) the skip‑rate drops 7 pts versus a generic headline. Does letting users tag their intent at the top of a digest boost consumption?
We tried something similar with allowing users to select topics of interest, but saw only a 2pt drop in skip-rate; what was the sample size for your experiment?
That's fascinating, did you control for the type of content or industry in the experiment? I'd love to know if the effect varies across domains.