My experience with Copilot is the other way around. I spend time writing my types/data structures, my functions, then Copilot tends to easily spit several variations of the test by just me giving it the name of the test.
Won't the prompt itself be the test? TDD is literally just providing an expected output on a given input, before implementing the functionality. The prompt we give AIs follows the same pattern, "I have a data that looks like ___, visualize it in a graph that ____"
Write your tests/expectations and the tooling automatically prompts/writes the code to meet the tests.