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)
Apple Messages integration with rich actions (verified)
WhatsApp messaging with read receipts
Telegram messaging (excl. Italy/Brazil)
Email management: read, search, draft, send (Gmail & Outlook)
Calendar management: schedule, check availability, recurring events
Reminders via text or voice
Web search with verified sources
Notion integration: pages, databases, docs
Oura integration: sleep, readiness, activity
TripIt automation for travel plans
Generate tables and charts from data or images
Poke Recipes for automations and integration setup
Poke Kitchen for custom developer integrations
@poke.com email address setup
