←Search results

Search “RAG”

By relevance · Total 3412 results Clear search

Saturday

Friday

  9. LiveKit Product and Engineering Blog

    How LiveKit builds production-grade AI voice agents

    LiveKit has released a guide sharing the experience of its solutions architects and forward-deployed engineers in helping customers move voice agent POCs into production systems, centered on three questions: whether the agent is smart and natural enough, whether production performance can be observed, and whether it can scale reliably and at low cost. The guide offers 7 methods, including measuring first-turn response latency separately, splitting context into the part needed for the greeting and the part loaded in the background, and enabling turn_detection=inference.TurnDetector() and adaptive interruption handling by default.

    Sequence diagram of an agent handling an async claim status lookup: it starts the lookup in the background, keeps talking with the caller, and reports back once the lookup finishes

    LiveKit has released a guide sharing the experience of its solutions architects and forward-deployed engineers in helping customers move voice agent POCs into production systems, centered on three questions: whether the agent is smart and natural enough, whether production performance can be observed, and whether it can scale reliably and at low cost. The guide offers 7 methods, including measuring first-turn response latency separately, splitting context into the part needed for the greeting an

    Matched fieldsBody

    #company#Tutorials / practice#Speech#Agents