Building a Codebase Classifier with Jev
A developer shares building a codebase classifier with Jev, suggesting it may solve overengineered code from agents, and asks what to test next.
A comment suggests using PromptQL directly, allowing tasks to run across multiple models including the cost-efficient Jev.
I'd just use PromptQL. You don't have to stick to one model. You can, in fact, have it run a task using multiple models (including the major cost saving Jev)