How it works

Architecture

Five admission checks decide whether a call is answered, and the answer waits at most a second for warm-up. PSTN and WebRTC build the same pipeline.

Four things matter before you build on Vertical AI. An admission sequence decides whether a call is answered. Both transports share one pipeline. Some surfaces trigger the post-call chain and some do not. And the version boundary splits settings a version owns from settings that edit live. For which region each part of that pipeline runs in, read where a Vertical AI call runs.

What happens when a call arrives

The caller's network delivers the call to our carrier, which posts a signature-verified webhook to the voice runtime. Everything below happens before the caller's phone stops ringing.

Number resolution

The runtime resolves the dialled number to an agent. If the lookup fails or the number is not assigned, the call is refused cleanly and the caller can redial.

Admission checks

Five checks decide whether the call is answered. They run concurrently with warm-up, so on the healthy path they cost no perceptible time.

CheckOn failureOn error
Blocked callerThe call is refused, or the caller hears your message and the call endsFails open
BillingCall refused before answer, no chargeFails open
Answering hoursOutside your hours, the call gets your closed handling: a message or a forwardFails open
Duplicate callSecond arrival for the same call refusedFails open
Platform capacityCaller forwarded to your overflow numberFails open

Blocked callers and answering hours apply only when the agent sets them. The duplicate guard is off by default. Billing and capacity are always active.

Order matters. The results are read in the order above, so a workspace that can't be billed is refused rather than forwarded. A pipeline slot is claimed while the checks run, and a call that any check turns away gives its slot back.

Warm-up during ringback

While the checks run, the runtime loads the agent's settings, warms the prompt cache and pre-renders the greeting audio. The answer waits at most a second for the warm-up; after that the call is answered anyway.

The caller hears ringback rather than dead air. A greeting rendered in advance is the difference between an agent that starts talking and one that starts thinking.

Answer and media

The runtime answers, the media stream opens, the greeting plays, and the conversation begins. Latency targets are on Reliability.

Two transports, one pipeline

TransportUsed by
PSTNInbound calls, outbound campaigns, onboarding, call-me test
WebRTCIn-app test call, share-link voice call, website voice widget

Both build the same pipeline. A browser test call exercises the same agent and conversational machinery as a phone call. What it does not exercise is the carrier leg: line quality, codec compression and speakerphone echo only show up on a real phone call.

After the call

Three passes run in order:

  1. Deterministic metrics. Model-free measurements from the call record.
  2. Judge metrics. A language model grades only the metrics the agent has enabled. None enabled means no model calls and no charge.
  3. Analysis. Sentiment, outcome, caller type, urgency, summary and extracted facts. Rolls the call into the caller profile when memory is on.

Analysis reads metric results, so it runs after the judge pass. Each pass is isolated, so one failing does not stop the next.

On the first analysis only, the platform fans out to alerts, post-call follow-up, the agent's post-call functions and the call_log.completed webhook. Re-analysis does not fire them again. Turning call analysis off also stops all of them.

Which surfaces run the post-call chain

SurfaceTransportPost-call chain
Real inbound or outbound callPSTNYes
In-app test call, share link, website widgetWebRTCYes
Voice eval, phone modePSTNYes, simulated
Voice eval, bridge modeDirectYes, simulated
Text evalNoneYes, simulated
Chat: test panel, share link, website widgetNoneNo

A phone-mode eval dials the agent's own number, so its agent leg is an ordinary inbound call. Every eval runs the chain marked simulated: metrics and analysis are written, and each post-call function records what it would have sent instead of sending it. So a test can't send a real message to a stranger.

Evals send nothing after the call

An eval sends no webhook, raises no alert and runs no follow-up. If your integration depends on those, check it on a real call.

On this page