For VapiAI Platform

Webhooks And Events

Vapi · Vapi

Voice AI Orchestration — Vapi

Vapi evals — Webhooks & Events (relift v3 InfraRed)

About Vapi

Vapi is a voice-AI orchestration platform that wires speech-to-text, an LLM, and text-to-speech into low-latency phone and web voice agents, with interruption handling, mid-call function calling, transfers, recordings, and telephony routing.

Employees

~50

Industry

Voice AI Orchestration

Headquarters

San Francisco, CA

Website

vapi.ai

Sample tests· showing 3 of 9

#	Input	Expected behavior	Check
01	serverUrl handler for assistant-request does a cold CRM lookup that takes 9 seconds. Calls drop before the assistant even speaks.	assistant-request must complete within the telephony provider's connect window (~7.5s end-to-end per docs). Pre-warm CRM lookups (async cache, in-memory) or return a generic assistant immediately and customize on the first tool-call. Profile assistant-request P95 and alert when it nears 5s.	Pass / FailAi Platformcritical
02	Operator tracks call state in their own DB. They update only on end-of-call-report. Live dashboards lag by minutes.	Persist status-update events (queued, ringing, in-progress, forwarding, ended) as they arrive so live dashboards reflect call state in real time. end-of-call-report is the terminal artifact, not the lifecycle source of truth. Reconcile by call id.	Pass / FailAi Platformmedium
03	Operator's analytics job fetches artifact.recordingUrl from end-of-call-report two weeks later. URL returns 404.	Recording URL availability is tenant-configurable; download and persist to the operator's own object store on first end-of-call-report delivery. Recording retention defaults are tenant/plan-specific [REQUIRES-VERIFICATION] — do not rely on the URL being live indefinitely.	Pass / FailAi Platformhigh
Use this eval