Poised Genie
Featured work · Avyra

An AI-native stack for places people walk into.

Avyra is a separate company building seven services that share one brain — vision sees the guest, the brain decides, the avatar speaks, the room bridge listens, the voice agent answers the phone, the POS rings it up, and the dashboard tells the operator what just happened. Poised Genie is the engineering team behind it. The pages that follow describe what we shipped.

How it fits together

One contract. Many surfaces.

Every Avyra service publishes and subscribes through a single Redis-backed event bus. avyra:presence:{tenant} is who's in the room. avyra:utterance:{tenant} is what gets said. avyra:speech_state:{tenant} keeps the mic and the speaker from talking over each other. No hardcoded copy lives in any room device — every word comes from the brain.

  • Vision publishes presence events from a USB camera.
  • Room-bridge mediates mic, VAD, STT, and turn-taking.
  • AI-engine decides what to say and when to transfer.
  • Avatar speaks with lip-synced wave rings.
  • Voice AI handles the phone with the same brain.
  • Dine + POS settle the actual transaction.
Guest walks in
        │
        ▼
[ avyra-vision ]  ─ publish presence ─►  Redis
                                          │
                  ┌───── subscribe ───────┤
                  ▼                       ▼
          [ avyra-room-bridge ]    [ avyra-avatar ]
                  │                       ▲
                  ▼                       │
       ┌──── /api/room/turn ──── [ ai-engine ]
       │                                  │
       ▼                                  ▼
 [ STT :8001 ]                     [ TTS :8002 ]
                                          │
                                          ▼
                                   Speaker / phone

Phone calls follow the same path,
just terminated by Asterisk + PJSIP.
The products

Pick one. Or run the whole suite.

Each Avyra product ships as its own service with its own contract. Adopt one for an immediate win, or compose the full room when you're ready.

Production

Avyra Dine

Restaurant ordering, reimagined.

QR-to-order, kitchen display, and seat-level billing — a full restaurant flow that pairs cleanly with Voice AI for phone orders.

Explore
Production

Avyra POS

Convenience-store ops without the spreadsheet pain.

Bulk inventory by Excel, physical counts with live value tracking, sales analytics, and hardware integrations — built for variety/tobacco shops.

Explore
Production

Avyra Voice AI

A receptionist that picks up every call.

Self-hosted phone agent: STT → LLM → TTS in under 800ms. Books appointments via Google Calendar, answers FAQs with RAG, triages emergencies, and warm-transfers to staff.

Explore
Production

Avyra Vision

Eyes for the room.

YOLO-based presence detection that publishes entered/left events on Redis — feeds greeters, avatars, and the brain. Pluggable face recognition for personalized welcomes.

Explore
Beta

Avyra Dashboard

One pane of glass for every tenant.

Operator console for the entire suite — call logs, intent breakdowns, latency histograms, occupancy, and revenue. Multi-tenant by design.

Explore
Production

Avyra Avatar

A visible presence on the screen.

Full-screen audio-reactive wordmark inside concentric wave rings. Idles gently, ripples to TTS audio, pulses on entry. The face of every Avyra room.

Explore
Production

Avyra Room Bridge

Where the room meets the brain.

Mic + VAD + STT + echo cancellation, orchestrating two-way conversation between vision, avatar, and the ai-engine. No hardcoded copy — every word comes from the brain.

Explore
Ready when you are

Got a product to build? Tell us what you have in mind.

We kick off in days, not months. Working software in weeks. If we're not the right fit, we'll tell you up front.