Skip to Content
cuelo.

05Observe

Observe

Every call is a stream of events — replay it in the dashboard, react to it in code, keep it in your database.

Voice agents fail in ways logs don't show: a reply that came 400 ms late, an interruption that wasn't, a tool that silently timed out. Cuelo records every step of every call as an ordered stream of events, plus both audio channels.

A live callstt · controller · policyllm · tool · tts events, in orderStoreSQLite · Postgres · MySQLDashboardreplay, latency, eventson_eventyour hook: logs, webhooksClientsRealtime & PCM streams + recordings: user.wav, agent.wav
one stream of events per call, fanned out to everything that watches.

Three ways to use it

Dashboard

Replay any call with both channels and the transcript, see every turn-taking decision, and break latency down per turn.

Events and hooks

on_event in src/events.py gets every event as it happens, for logs, webhooks, analytics and alerts.

Storage

SQLite by default, Postgres or MySQL in production, recordings on disk, and a read-only JSON API over all of it.

A debugging loop that works

  1. Make a test call and open it in the dashboard.
  2. Check the latency tab: which stage dominates TTFB? vad_tail points at end-of-turn tuning, llm_ttft at the model or the prompt length, and tts_ttfa at the voice provider.
  3. Check flags: premature replies mean turn ends fire too early, and slow turns are listed with their cause.
  4. Change one thing in config.cuelo. cuelo dev reloads it.
  5. Call again and compare.

Custom endpoints

Your own HTTP and WebSocket routes next to the Realtime API — telephony, webhooks, app protocols.

Dashboard

Replay every call, see every decision, and try your agent live.

On this page

Three ways to use itA debugging loop that works