Hospitality Staff Copilot
Outcome
Equip frontline hospitality staff to resolve guest requests on the spot using property knowledge, standard operating procedures, reservation context, and guest preferences, with manager approval for compensation beyond service authority.
| Portfolio attribute | Value |
|---|---|
| Primary persona | Frontline employee |
| Primary aggregate | GuestServiceRequest |
| Cosmos DB containers | 3 |
| Grounding data | PMS and CRS reservations, room state, loyalty and consented preferences, contact-center history, property knowledge, SOPs, housekeeping and engineering work orders, point-of-sale and partner events |
| Development estimate | USD 60-220 monthly dev estimate |
| Runtime options | Python FastAPI and C# ASP.NET Core |
Productivity hypothesis
These measures reflect the workflow, evidence, decision boundary, and industry risk for this use case.
| Impact type | Measure | Conservative internal assumption | Customer measurement |
|---|---|---|---|
| Productivity | Guest issue response time | 15-25% reduction | (baseline median guest-issue response minutes - assisted median minutes) / baseline median minutes * 100 |
| Quality or risk | SLA breach or compensation leakage rate | 5-10% reduction | (baseline SLA-breach or compensation-leakage rate - assisted rate) / baseline rate * 100 |
Important: Conservative internal pilot assumptions only; not public benchmarks, commitments, or expected customer results. Validate against a comparable baseline or matched control cohort with mandatory human review.
Rationale: Room, work-order, guest, and SOP context supports faster safe frontline action.
Pilot guardrail: Managers approve compensation above authority limits, and the assistant must not make silent property-system changes.
Customer validation plan
- Baseline the current workflow with representative users and tasks.
- Run the accelerator on the same task mix with human review retained.
- Measure guest issue response time and sla breach or compensation leakage rate with the documented formulas.
- Replace internal assumptions with customer-observed results before a business case.
Why Azure Cosmos DB
This AI solution needs an operational data plane, not only a vector index:
- Hybrid vector and full-text retrieval combines semantic recall with exact identifiers, codes, names, and domain language.
- Hierarchical partition keys and metadata predicates keep tenant and domain boundaries in the normal query path.
- Operational JSON, source chunks, workflow and agent state, feedback, and audit records remain together for low-latency reads and governed writes.
- Change feed reacts to source and operational updates without polling.
- Autoscale throughput, configurable consistency, and multi-region distribution support variable demand and enterprise availability.
Domain workflow

| Stage | Actor | Input → output | Approval |
|---|---|---|---|
| 1. Capture the guest request | Frontline employee | Guest message, call, or in-person request → GuestServiceRequest with room and urgency | Policy controlled |
| 2. Load reservation and guest preferences | Stay context service | Reservation identifier and guest profile → Stay context with inclusions and preferences | Policy controlled |
| 3. Retrieve property knowledge and SOP | Retrieval agent | Request kind and property scope → Verified property facts and applicable SOP steps | Policy controlled |
| 4. Guide the resolution at the point of service | Hospitality copilot | SOP steps, inclusions, and preferences → Cited response with the staff member's authority limit shown | Policy controlled |
| 5. Approve compensation beyond authority | Duty manager | Proposed ServiceRecoveryAction and value → Approved gesture posted to the folio with justification | Human required |
Technical architecture

Cosmos DB data model
| Container | Hierarchical partition key | Documents | Search paths |
|---|---|---|---|
guestServiceRequests | /tenantId, /propertyId | GuestServiceRequest, ReservationContext, PropertyKnowledgeItem, ServiceRecoveryAction | /requestTextVectorEmbedding, /bodyVectorEmbedding, /requestTextVector, /bodyVector |
hospitalitySopLibrary | /tenantId, /requestKind | StandardOperatingProcedure | /stepVectorEmbedding, /stepVector |
guestProfileStore | /tenantId, /guestProfileId | GuestPreferenceRecord | Operational fields only |
Query contract
| Query | Container | Scope | Purpose |
|---|---|---|---|
| In-stay service context | guestServiceRequests | single-partition | Read the open requests and the reservation context for the stay in one partition-aligned query. Guest preferences follow the guest across properties, so they are read from the guestProfileStore container by guestProfileId instead of being duplicated into every property partition. |
| Currently valid property facts | guestServiceRequests | single-partition | Return only property knowledge that is in its validity window and recently verified. |
| Request-kind SOP retrieval | hospitalitySopLibrary | single-partition | Knowledge-container query against hospitalitySopLibrary (partition-aligned to /tenantId + /requestKind): pull the SOP steps and authority limits for the specific request type; the library stores one SOP document per request kind so the lookup is a single partition read. |
| Pending manager approvals | guestServiceRequests | single-partition | Show service recovery gestures waiting on duty-manager sign-off. |
Python and C# services route each document type to its declared container and hierarchical partition key. ETag-based writes protect mutable aggregates, while append-only records and bounded cross-partition queries preserve scale.
Azure deployment

Clone the source repository, authenticate with Azure, and run:
Set-Location accelerators/travel-hospitality/hospitality-staff-copilot
az login
./Deploy.ps1 -Runtime python -Location eastus2
Change python to csharp to deploy the .NET implementation.
Explore the implementation
- Launch signed-in demo
- Implementation article
- Domain data model
- Workflow and API contract
- Python application
- C# application
- Domain container Bicep
- Platform Bicep
- Cost and configuration
- Source repository