# Overview LoopDesk sits between your AI pipeline and your end users. Every AI-generated decision flows through a confidence and risk gate; the edge cases get routed to a human reviewer before they ship. ## The loop ``` INPUT DATA → AI SYSTEM → [confidence + risk routing] → HUMAN (when needed) → DECISION ``` * **Auto-approve** high-confidence, low-risk items * **Queue for review** anything that crosses a threshold * **Escalate** sensitive actions (payments, refunds, moderation) * **Capture overrides** as training signal so the queue shrinks over time ## Who it's for Teams running AI in production where blanket auto-approval is unsafe and blanket human review is too slow: * Customer support replies * Content moderation * Invoice classification * Legal summaries * Product copy compliance --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://hitl-01.gitbook.io/hitl-docs/getting-started/overview.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.