You will never really be able to prove (or show, or demonstrate) that something works if you invite people for a survey and ask them "what do you think about this?".
After running interviews and surveys, prepare a test that clearly states: this is not a test.
In practice, that means introducing a change and measuring its effects in comparison to the original state of things. This is the only way to demonstrate without a doubt that your design task, your new service or your innovation project actually causes behaviour change.