Ask HN: When did you move from AI agentic loops to simpler deterministic system?

Industry is increasingly moving towards complex, autonomous agentic loops and feedback chains. They obviously comes with significant latency, non-determinism, low-accuracy and cost.

I'm interested in hearing from engineers who have moved in the opposite direction.

At what point in your product lifecycle did you decide that agentic approach was wrong tool for the job?

What was the specific failure mode (reliability, cost, latency, maintainability) pushed you to replace agentic loop with more deterministic system/pipeline?