Time-box experiments to learn fast

In this context, "fishing" means putting out initial exploratory efforts to test a new marketing channel and see if there's any promising response, similar to testing the waters.

Generally I wouldn't let anything bleed past a quarter. You can probably get some good signal in a month or less, what I would call fishing.

My rule of thumb, if we cannot collect the sample size in the month, we shouldn't test it, period. Because it's just then it's not fast enough.

If you can time box it to three months, what can I do at the end of three months? Is this likely to work or not?

If you cannot collect the sample size in a month, we shouldn't test it, period. Because it's just then it's not fast enough.