Experiments prompting people to engage in more prosocial behavior (e.g., acts of kindness) or simple social interactions (e.g., acting extraverted) have both shown promise in boosting well-being. However, little is known about how much the impact on well-being depends on the type of interpersonal interaction (i.e., social vs. prosocial) or on other proximal features (e.g., whether the interaction takes place online vs. in-person, the closeness of the relationship, or amount of social connection associated with a given interaction). We randomly assigned a sample of full-time employees recruited via a special employed mTurk sample (N = 754) to perform weekly acts of kindness online versus in-person, to engage in weekly social interactions online versus in-person, or to list their daily activities (control) over the course of 4 weeks. First, on average, all conditions reported improvements in well-being (i.e., increases in positive affect and life satisfaction, decreases in negative affect) across the 4-week intervention period. Second, relative to controls, the four experimental groups reported increases in general social connectedness over time. Finally, according to auxiliary analyses collapsed across the experimental condition, closer relationship with target and non-digital medium of delivery predicted episode-level social connection, which, in turn, was associated with general social connectedness and positive affect. We conclude that the "who" and the "how" of a behavior (i.e., its target, its delivery method, and the feelings of social connection generated) are important for well-being, but not the "what" (i.e., whether the behavior is social or prosocial). (PsycInfo Database Record (c) 2023 APA, all rights reserved).