User Journey
From a question to a cited answer — or an honest escalation to the right human team.
From a question to a cited answer
An employee asks an operational question in their own words. The pipeline loads session context, classifies intent and decides whether to clarify first, then rewrites the question for retrieval while preserving exact tokens like form codes and policy numbers.
Hybrid retrieval pulls candidates by semantic similarity and exact keyword match; a cross‑encoder reranks them down to the few best passages. The evidence‑sufficiency gate then asks a simple question — is this good enough to answer? If yes, the model generates an answer drawn only from those passages, with inline citations and a confidence score, and a verification pass claim‑checks each assertion before anything reaches the employee.
When the honest answer is “not confident”
If the gate says no, the employee sees an honest reply with two choices: retry, or escalate to the suggested team. Escalating creates an entry in the console queue with the full thread, the retrieved evidence and the draft attached — the human picks up exactly where the assistant left off.