Bayesian experimental design is like when you get to pick how you want to do an experiment before you even start it. It's like planning a puzzle before you put it together.
So, let's say you want to do an experiment to figure out how many blue M&M's are in a bag. You can't count every single M&M because there are too many! That would take forever. So instead, you decide to count a few of them and then use math to guess how many blue M&M's are in the whole bag.
But how do you decide which M&M's to count? That's where Bayesian experimental design comes in. You get to use math to figure out the best way to pick which M&M's to count.
It's like if you were picking puzzle pieces to put together. You want to pick the pieces that will help you finish the puzzle faster, right? With Bayesian experimental design, you figure out which M&M's will give you the most information about how many blue M&M's are in the whole bag.
So you use math to pick which M&M's to count, and then you use math again to guess how many blue M&M's are in the whole bag based on the ones you counted. And that's how you do a Bayesian experiment!