GA keeps good tries, mixes them, and adds random changes.
GA is like a toy-car race in a garage. Keep the fast cars, swap their parts, and sometimes add a weird rocket.
It hunts a huge pile of choices for a better answer. It helps with routes and schedules. It also picks AI settings.
Optimization
GA is an optimization method for finding better answers in a huge space.
Heuristic Search
GA uses evolution-style trial and error, not a full check of every answer.
HPO
GA can automatically try different hyperparameter mixes.
No Free Lunch Theorem
The No Free Lunch Theorem says GA is not best for every problem.