You are missing a very important part of how science is done: science starts with a hypothesis, the refutation or confirmation of that hypothesis is done by experiment. Plenty of science has been locked into the theoretical phase for decades before experimental verification could be obtained.
If all we did was experiments we'd surely find some interesting stuff but without theory to guide where to do the next set of experiments science would be very inefficient. It's the closing of the loop that powers this tremendous progress you see from the renaissance to today.
Without that we'd be stuck in alchemy, astrology and other pseudo sciences.
Science must find a balance between extremes in how experimental resources are invested:
Extreme “Exploitation” Bias: “For maximally economical progress, experimental physics must strictly stay within the hard boundaries established by theoretical frameworks.”
Extreme “Exploration” Bias: “For maximally fundamental progress, experimental physics must question all theoretical assumptions and boundaries with extreme suspicion.”
It makes sense to diversify the kind of experimental investments we make along this risk/reward or exploration/exploitation spectrum. There are unique dangers if we weight too heavily on either extreme.
I think there's one more step that goes a bit earlier in the process. Before an observation is made, there needs to be a choice on what experiments are done. Typically, those measurements will be done with one of two goals. The first is to measure a free parameter in the theory that isn't well-constrained by existing experiments. (e.g. "According to Maxwell's equations, the speed of light should be constant. Let's measure that constant value." [0]) The second is to find an unintuitive prediction from current models, then measure what happens in those circumstances. (e.g. "According to special relativity, passage of time should vary based on velocity. That's weird. Let's measure and see if it is the case." [1])
The purpose of these is to narrow down which experiments are being performed, trying to choose experiments that will try their hardest to break an existing theory.
[1] https://en.wikipedia.org/wiki/Hafele%E2%80%93Keating_experim... (This article currently has an incorrect edit made yesterday. It seems to be based on a mistaken assumption that the rotating earth is a stationary reference frame. The opening paragraph should read "were consistent" rather than "were not consistent".)
If all we did was experiments we'd surely find some interesting stuff but without theory to guide where to do the next set of experiments science would be very inefficient. It's the closing of the loop that powers this tremendous progress you see from the renaissance to today.
Without that we'd be stuck in alchemy, astrology and other pseudo sciences.