We (my company) are trying to create agents that read a story and translate that into prompts, then execute said prompts, then review the output. The only piece missing is accepting the merge.

I'm not anti-AI, but a human needs to be involved at every step because a minor mistake made at the first step will amplify through the agentic pipeline.

A human should review every single thing that comes out of AI — especially if it is to be fed back into AI.