Features
Multi-turn agent simulations with LLM-powered user simulator
Per-turn judge agent with pass/fail criteria
Adversarial red-teaming (Crescendo escalation, refusal detection)
Voice agent testing with latency metrics and noise injection
Tool-call verification across long dialogues
Framework-agnostic adapters (LangGraph, CrewAI, Pydantic AI, etc.)
Run locally or in CI/CD (pytest/vitest)
Visual debugger for simulation replay
Pause, evaluate & annotate mid-conversation
Open-source Scenario SDK (Python + TypeScript, MIT)
Langy: AI assistant to generate test plans from plain-English goals
Prompt Registry with versioning and A/B testing
AI Governance: virtual keys, budgets, routing policies, audit trail
Event sourcing engine for real-time processing of traces, evals, simulations
Self-host with ClickHouse (no Elasticsearch required)
No-code visual workflow builder
Omnichannel deployment (web, phone, mobile)
Low-latency voice (500ms)
High throughput (300k messages/min)
Integrated prototyping and NLU modeling
Entry conditions for playbooks/workflows
Required variables for workflows
Organization-level usage breakdown
Voiceflow Core optimized model (May 2026)
Transcript filtering by workflow and tool
