By skyforbes I’m trying to build an AI agent that helps refine creative prompts for video generation (Sora). The idea is that instead of just taking a single prompt, it would ask clarifying questions (e.g., “What mood are you going for?” or “Do you want it cinematic or realistic?”), remember previous answers, and then generate a refined final prompt or even trigger video generation.
I’m wondering what’s the best way to approach this. Also curious if anyone’s tried something similar for creative tools or video workflows.