By Sagar Shankaran, Founder of CallSphere
A technical deep dive into CallSphere's 11-agent hotel architecture — the specialists, their tools, handoff logic, and PMS integration layer.
Key takeaways
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.
lookup_guest_by_phone, detect_intent, get_hotel_info, route_to_agentsearch_availability, quote_rate, check_parity, collect_guest_details, process_deposit, create_reservationverify_reservation, capture_incidentals, issue_mobile_key, assign_roompull_folio, dispute_charge, capture_payment, email_receipt, post_loyalty_pointsupdate_room_status, create_maintenance_ticket, assign_cleaner, report_inspectioncreate_service_request, schedule_wake_up, book_restaurant, extend_check_out, book_activitycheck_block_inventory, draft_proposal, schedule_site_visit, notify_dosmanalyze_demand, check_parity, alert_revenue_managerpush_rates, sync_inventory, handle_overbookinglookup_loyalty, apply_discount, trigger_upgrade, log_preferencelate_check_in, verify_identity, classify_emergency, escalate_to_on_callHandoffs use OpenAI Agents SDK's hierarchical handoff mechanism. Each handoff carries:
flowchart LR
CALLER(["Guest or Prospect"])
subgraph TEL["Telephony"]
SIP["Twilio SIP and PSTN"]
end
subgraph BRAIN["Hotel Concierge AI Agent"]
STT["Streaming STT<br/>Deepgram or Whisper"]
NLU{"Intent and<br/>Entity Extraction"}
TOOLS["Tool Calls"]
TTS["Streaming TTS<br/>ElevenLabs or Rime"]
end
subgraph DATA["Live Data Plane"]
CRM[("CRM and Notes")]
CAL[("Calendar and<br/>Schedule")]
KB[("Knowledge Base<br/>and Policies")]
end
subgraph OUT["Outcomes"]
O1(["Reservation confirmed"])
O2(["Room service order"])
O3(["Front desk handoff"])
end
CALLER --> SIP --> STT --> NLU
NLU -->|Lookup| TOOLS
TOOLS <--> CRM
TOOLS <--> CAL
TOOLS <--> KB
NLU --> TTS --> SIP --> CALLER
NLU -->|Resolved| O1
NLU -->|Schedule| O2
NLU -->|Escalate| O3
style CALLER fill:#f1f5f9,stroke:#64748b,color:#0f172a
style NLU fill:#4f46e5,stroke:#4338ca,color:#fff
style O1 fill:#059669,stroke:#047857,color:#fff
style O2 fill:#0ea5e9,stroke:#0369a1,color:#fff
style O3 fill:#f59e0b,stroke:#d97706,color:#1f2937
Each property ingests policy documents (cancellation, pet, parking, amenity, etc.) into ChromaDB. Agents query ChromaDB for accurate policy citation instead of hallucinating.
Hear it before you finish reading
Talk to a live CallSphere AI voice agent for hospitality in your browser — 60 seconds, no signup.
Multiple guardrails prevent hallucination:
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.
Still reading? Stop comparing — try CallSphere live.
See the hospitality AI agent handle a real call — complete, industry-specific, and live in your browser. No signup.
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
Written by
Sagar Shankaran· Founder, CallSphere
LinkedInSagar Shankaran is the founder of CallSphere, where he builds production AI voice and chat agents deployed across healthcare, hospitality, real estate, and home services. He writes about agentic AI, LLM engineering, and shipping voice agents that handle real calls in production.
See how AI voice agents work for your industry. Live demo available -- no signup required.
Five proven multi-agent architecture patterns built on A2A — orchestrator, peer mesh, hub-and-spoke, marketplace, and tiered specialist.
How to design a multi-agent system using MCP for tools and A2A for cross-vendor coordination, with a CallSphere voice agent as a participating node.
A2A is the open standard for agent-to-agent coordination. Here is how the Agent Card JSON works, how discovery happens, and what to publish.
A2A unlocks cross-vendor agent coordination, but most enterprise voice/chat workloads still ship faster on a single-vendor stack. Here is how to choose.
Every 100ms of latency costs you. So does every cent per minute. Here is the decision matrix we use across 6 verticals to pick where to spend and where to save on voice AI infrastructure.
When to use Pinecone vs pgvector vs Qdrant vs Weaviate. A decision framework that maps team size and workload to the right pick without endless evaluation loops.
© 2026 CallSphere Inc. All rights reserved.
Made within San Francisco
Watch how CallSphere handles real customer calls, schedules appointments, and processes payments — live.
Try Live DemoBook a DemoCalculate Your ROI