Inside the CallSphere Hotel Stack: 11 Specialist Agents + Tools

TL;DR

CallSphere's hotel platform is built on OpenAI Agents SDK + Realtime API with 11 specialist agents, each with dedicated tools and handoff logic. Here is the full technical architecture.

Framework Choice

• Voice: OpenAI Realtime API (GPT-4o-realtime-preview)
  • PCM16 24kHz audio
  • Server VAD turn detection
  • Sub-1-second latency
• Orchestration: OpenAI Agents SDK (hierarchical handoffs)
• Analytics: GPT-4o-mini for post-call sentiment, intent, and summarization
• Telephony: Twilio (voice) + SIP trunking
• Backend: Python FastAPI + NATS message queue
• Storage: PostgreSQL (primary), Redis (cache), ChromaDB (RAG)

The 11 Agents

1. Concierge Agent (Triage)

• Model: GPT-4o-realtime
• Tools: lookup_guest_by_phone, detect_intent, get_hotel_info, route_to_agent
• Handoffs: all other agents

2. Reservation Agent

• Tools: search_availability, quote_rate, check_parity, collect_guest_details, process_deposit, create_reservation
• Integrations: PMS, channel manager, payment processor

3. Check-In Agent

• Tools: verify_reservation, capture_incidentals, issue_mobile_key, assign_room
• Integrations: PMS, Salto/Assa Abloy/Dormakaba, Stripe

4. Check-Out Agent

• Tools: pull_folio, dispute_charge, capture_payment, email_receipt, post_loyalty_points

5. Housekeeping Agent

• Tools: update_room_status, create_maintenance_ticket, assign_cleaner, report_inspection

6. Guest Services Agent

• Tools: create_service_request, schedule_wake_up, book_restaurant, extend_check_out, book_activity

7. Group Sales Agent

• Tools: check_block_inventory, draft_proposal, schedule_site_visit, notify_dosm

8. Revenue Signals Agent

• Mode: Passive observer, not guest-facing
• Tools: analyze_demand, check_parity, alert_revenue_manager

9. OTA Channel Agent

• Tools: push_rates, sync_inventory, handle_overbooking
• Integrations: Siteminder, Cloudbeds, Derbysoft

10. Loyalty Agent

• Tools: lookup_loyalty, apply_discount, trigger_upgrade, log_preference
• Integrations: Marriott Bonvoy, Hilton Honors, etc.

11. Night Audit + Emergency Agent

• Tools: late_check_in, verify_identity, classify_emergency, escalate_to_on_call
• Runs: 12 AM–7 AM autonomously

Handoff Logic

Handoffs use OpenAI Agents SDK's hierarchical handoff mechanism. Each handoff carries:

flowchart TD
    START(["Inside the CallSphere Hotel Stack: 11<br/>Specialist Agents + Tools"])
    S0["TL;DR"]
    START --> S0
    S1["Framework Choice"]
    S0 --> S1
    S2["The 11 Agents"]
    S1 --> S2
    S3["Handoff Logic"]
    S2 --> S3
    S4["RAG for Policy Questions"]
    S3 --> S4
    S5["Guardrails"]
    S4 --> S5
    S6["FAQ"]
    S5 --> S6
    DONE(["Key Takeaways"])
    S6 --> DONE
    style START fill:#4f46e5,stroke:#4338ca,color:#fff
    style DONE fill:#059669,stroke:#047857,color:#fff

• Full conversation history
• Guest profile context
• Current PMS state
• Previous agent notes

RAG for Policy Questions

Each property ingests policy documents (cancellation, pet, parking, amenity, etc.) into ChromaDB. Agents query ChromaDB for accurate policy citation instead of hallucinating.

flowchart TD
    HUB(("Hospitality Venue"))
    HUB --> A["24 by 7 call coverage<br/>in 57 plus languages"]
    HUB --> B["Sub second response<br/>with natural voice"]
    HUB --> C["Direct booking into<br/>your calendar and CRM"]
    HUB --> D["Smart escalation when<br/>a human is needed"]
    HUB --> E["Sentiment and intent<br/>analytics on every call"]
    HUB --> F["One flat monthly fee<br/>no per minute billing"]
    style HUB fill:#4f46e5,stroke:#4338ca,color:#fff
    style A fill:#e0e7ff,stroke:#6366f1,color:#1e293b
    style B fill:#e0e7ff,stroke:#6366f1,color:#1e293b
    style C fill:#e0e7ff,stroke:#6366f1,color:#1e293b
    style D fill:#e0e7ff,stroke:#6366f1,color:#1e293b
    style E fill:#e0e7ff,stroke:#6366f1,color:#1e293b
    style F fill:#e0e7ff,stroke:#6366f1,color:#1e293b

Guardrails

Multiple guardrails prevent hallucination:

• Input validation (language detection, intent confidence)
• Tool call validation (schema enforcement)
• Output validation (policy accuracy checks)
• Hallucination detection (comparing claims to RAG ground truth)

FAQ

Q: Is this open source? A: No. CallSphere is a managed SaaS.

Q: Can I use my own LLM? A: On enterprise plans, Claude and Gemini available as alternatives.

Q: What's the latency? A: <1 second first response, <200ms for tool calls.

---

Related: 11-agent stack overview | Hotel industry

#Architecture #MultiAgent #Technical #CallSphere