Travel & Hospitality

Hospitality Staff Copilot

Designed for Frontline employee

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.

Contract TRV-03 · primary aggregate GuestServiceRequest · mode loading

Decision brief

Approve compensation beyond authority: evidence ready for review

This brief starts with the decision, evidence, and accountable owner. The guided workflow then shows how the recommendation was produced.

Decision signals

The evidence and control points that shape this recommendation.

Decision owner

Duty manager

The named role remains accountable for the consequential decision.

Governed evidence

6 record types

Structured records and cited text ground the recommendation.

Workflow

5 controlled stages

Each transition records its input, output, status, and audit context.

Human controls

1 approval gate

Approval gates prevent the copilot from making consequential decisions.

Business problem

A guest messages at 22:40 that their room air conditioning is failing; the copilot shows the suite is on a package rate with late checkout included, cites the SOP requiring an engineering visit within 20 minutes and a room move if unresolved, surfaces the guest's prior noise complaint, and routes the proposed one-night rate adjustment to the duty manager because it exceeds the agent's authority limit..

Decision to make

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.

Outcome to show

Approved gesture posted to the folio with justification gives Duty manager the evidence needed to begin the final governed business outcome, with the decision trail retained for review.

  1. 1Capture the guest request
  2. 2Load reservation and guest preferences
  3. 3Retrieve property knowledge and SOP
  4. 4Guide the resolution at the point of service
  5. 5Approve compensation beyond authority

Step 1 of 5

Ready: Start with the business question, then use the single button above.

The output appears here immediately. More technical evidence remains available below.

System logic, GenAI, and human accountability

The demonstration keeps deterministic controls, AI assistance, and approval separate.

System logic

Source systems enforce identity, workflow order, policy filters, and record updates.

GenAI contribution

Retrieval and generation assemble relevant evidence into a cited recommendation or draft.

Human accountability

Duty manager verifies material claims and approves the consequential action.

Workflow stages

Run the stages in order before using the Copilot. Every stage explains what happens, why it matters, the evidence it uses, and the complete API request and response.

Seeded record
Loading
Document type
Loading
Container
Loading
Partition key
Loading
Current stage
Loading

API demonstration guidance

Run a stage to see its explanation, evidence, full request, and full response.

Grounded chat

Ask a question and receive an answer grounded in retrieved GuestServiceRequest evidence.

Answer and evidence

Select a starter question or enter your own.

Evidence

Domain implementation workspace

Loaded live from /api/config, /api/domain/model, and /api/domain/sample.

Domain objective
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.
Primary aggregate
GuestServiceRequest
Primary container
guestServiceRequests
Hierarchical key
/tenantId + /propertyId
Schema version
1

Sample scenario

A guest messages at 22:40 that their room air conditioning is failing; the copilot shows the suite is on a package rate with late checkout included, cites the SOP requiring an engineering visit within 20 minutes and a room move if unresolved, surfaces the guest's prior noise complaint, and routes the proposed one-night rate adjustment to the duty manager because it exceeds the agent's authority limit.

Physical Cosmos DB containers

Every container provisioned for this accelerator with its hierarchical partition key.
Container Role Hierarchical partition key Document types
guestServiceRequests Primary /tenantId + /propertyId GuestServiceRequest, ReservationContext, PropertyKnowledgeItem, ServiceRecoveryAction
hospitalitySopLibrary Reference /tenantId + /requestKind StandardOperatingProcedure
guestProfileStore Reference /tenantId + /guestProfileId GuestPreferenceRecord

Document types

Contract document types, their owning container, and their identifier pattern.
Type Container Partition key Identifier pattern Embedding fields
GuestServiceRequest guestServiceRequests /tenantId + /propertyId request::{propertyId}::{requestId} requestTextVector
ReservationContext guestServiceRequests /tenantId + /propertyId reservation::{propertyId}::{reservationId} None
PropertyKnowledgeItem guestServiceRequests /tenantId + /propertyId knowledge::{propertyId}::{itemId} bodyVector
StandardOperatingProcedure hospitalitySopLibrary /tenantId + /requestKind sop::{requestKind}::{sopId}::{stepIndex} stepVector
GuestPreferenceRecord guestProfileStore /tenantId + /guestProfileId guestpreference::{guestProfileId} None
ServiceRecoveryAction guestServiceRequests /tenantId + /propertyId recovery::{propertyId}::{actionId} None

Query patterns