Squad And Workflow Routing
Vapi · Vapi
Voice AI Orchestration — Vapi
Evaluates Vapi's Squad & Workflow Routing 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 | Operator creates a squad with three assistants: triage, billing, tech-support. They omit assistantDestinations on triage. Triage never hands off. | Each squad member declares assistantDestinations[] with destination assistant id, description (why transfer here), message (what triage says before handoff), and transferMode. Without assistantDestinations the member is a leaf — no outbound transfer. Round-trip GET /squad/{id} to verify. | Pass / FailAi Platformhigh |
| 02 | Triage has destinations 'billing' (desc: 'for billing questions') and 'collections' (desc: 'for billing questions'). Customers asking about refunds land randomly on either. | Descriptions must be distinct enough for the routing model to decide. Use specific phrasing: billing → 'invoice questions, charge disputes'; collections → 'past-due balance and payment plans.' Test routing with a held-out scenario set and inspect transferReason in artifact.messages[]. | Pass / FailAi Platformmedium |
| 03 | Triage transfers to billing. Billing assistant asks the customer to repeat their order number, even though they just gave it to triage. | Vapi propagates the in-call transcript / messages[] state to the destination assistant; configure the destination's system prompt to summarize prior context rather than restart. If full transcript carry-over is unclear [REQUIRES-VERIFICATION], pass key facts via messageResponse or dynamic variables… | Pass / FailAi Platformhigh |
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
- Squad And Workflow Routing
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 Squad And Workflow Routing eval for Vapi Vapi test?+
Evaluates Vapi's Squad & Workflow Routing 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 Squad And Workflow Routing 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 Squad And Workflow Routing 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 Squad And Workflow Routing 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.