Features
Natural language agent specification
Agent Contracts framework for reliability
Continuous evaluation (Continuous Eval)
Automated testing and verification
Reference-free and reference-based evaluation metrics
Synthetic data generation for benchmarking
RAG pipeline evaluation support
Granular evaluation of complex GenAI apps
Pre-built evaluators for correctness, faithfulness, relevance
Golden dataset management
Iterative refinement based on evaluation results
No prompt tweaking 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
