2 points | by hoverbot 15 hours ago ago
1 comments
Author here. We run chatbots with a smart router: classify noise/PII first, call retrieval+LLM only when needed, and use deterministic flows for actions. This keeps latency and cost down and makes behavior explainable. What would you add or change?
Author here. We run chatbots with a smart router: classify noise/PII first, call retrieval+LLM only when needed, and use deterministic flows for actions. This keeps latency and cost down and makes behavior explainable. What would you add or change?