Webhooks And Events
Vapi · Vapi
Voice AI Orchestration — Vapi
Evaluates Vapi's Webhooks & Events across 9 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Voice AI Orchestration eval coverage.
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.
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 serverUrl skips signature verification because 'it's behind a VPC.' An external pentester emulates the webhook and triggers a transferCall to a scammer number. | Verify the documented Vapi signature header on every inbound webhook before executing side effects (tool calls, CRM writes, transfers). The exact header name and HMAC algorithm should be confirmed against current docs [REQUIRES-VERIFICATION]. Reject mismatched signatures with 401. | Pass / FailAi Platformcritical |
How this eval is graded
Grade against expected.ideal_behavior and expected.rubric. Per-criterion pass requires mean >= 4.0 and no criterion below 3.
Rubric criteria
- Vapi
- Ai Platform
- Webhooks And Events
Recommended for
Works with
Related evals
Claude API
Evaluates Anthropic's Batch API across 9 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Foundation Model & API eval coverage.
View AI PlatformClaude API
Evaluates Anthropic's Extended Thinking across 9 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Foundation Model & API eval coverage.
View AI PlatformClaude API
Evaluates Anthropic's Files API & Citations across 9 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Foundation Model & API eval coverage.
ViewFrequently asked questions
What does the Webhooks And Events eval for Vapi Vapi test?+
Evaluates Vapi's Webhooks & Events across 9 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Voice AI Orchestration eval coverage.
How is the Webhooks And Events eval scored?+
The judge rubric: Grade against expected.ideal_behavior and expected.rubric. Per-criterion pass requires mean >= 4.0 and no criterion below 3.
How many test cases does this eval pack include?+
The Webhooks And Events pack for Vapi Vapi contains 9 test cases. 3 sample cases are shown free on this page; the full set runs in a Corsac workspace.
How do I run this eval?+
Sign up for Corsac, connect your model or agent endpoint, and run the Webhooks And Events pack as-is or after customizing thresholds. Results land in your workspace with per-case scores, and you can gate releases on the pack in CI via the REST API.
Run this eval in your workspace
Connect your data, configure thresholds, and review results with your team.