I want to make a simple solution where data is parsed by a vision model and "engineer for the unhappy path" is my assumption from the get-go. Changing the prompt or swapping the model is cheap.
vision models are also faulty, and some times all paths are unhappy paths, so there's really no viable solution. Most of the times, swapping the model completely randomizes the problem space (unless you measure every single corner case, it's impossible to tell if everything got better or if some things got worse...
