Skip to main content
TRV-01 · Travel & Hospitality

Personalized Trip Concierge

Outcome​

Turn a traveller's loose idea into a bookable, personalized itinerary by combining live inventory, rates, loyalty status, stated preferences, and destination knowledge, with explicit traveller confirmation before any booking is ticketed.

Portfolio attributeValue
Primary personaTraveler
Primary aggregateTripPlan
Cosmos DB containers2
Grounding dataCRS and booking records, GDS/NDC offers, PMS inventory, loyalty entitlements, consented traveler preferences, destination guidance, partner inventory, pricing and hold events
Development estimateUSD 60-220 monthly dev estimate
Runtime optionsPython FastAPI and C# ASP.NET Core

Productivity hypothesis​

These measures reflect the workflow, evidence, decision boundary, and industry risk for this use case.

Impact typeMeasureConservative internal assumptionCustomer measurement
ProductivityRequest-to-bookable-shortlist time10-20% reduction(baseline median request-to-shortlist minutes - assisted median minutes) / baseline median minutes * 100
Quality or riskPrice and change catch accuracy5-10 percentage-point improvementassisted percentage of material price or itinerary changes caught before confirmation - baseline percentage
Business outcomeOffer-to-book conversion3-8% relative improvement(assisted bookings per eligible shortlist - baseline 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: Grounded itinerary discovery can shorten shortlist preparation and modestly improve conversion among comparable qualified requests.

Pilot guardrail: Travelers confirm suppliers, availability, prices, and terms before booking or ticketing.

Customer validation plan​

  1. Baseline the current workflow with representative users and tasks.
  2. Run the accelerator on the same task mix with human review retained.
  3. Measure request-to-bookable-shortlist time and price and change catch accuracy with the documented formulas.
  4. 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​

Domain workflow

StageActorInput → outputApproval
1. Describe the trip ideaTravellerFree-text intent with dates, party, and budget hints → TripPlan with structured constraintsPolicy controlled
2. Ground suggestions in preferences and loyaltyPersonalization agentPreference profile and loyalty standing → Weighted suggestion criteriaPolicy controlled
3. Shop live inventory and ratesInventory shopping serviceCriteria, dates, and destination → Priced InventoryOffer set with hold expiryPolicy controlled
4. Assemble a coherent itineraryTrip conciergeOffers plus destination knowledge and travel times → Itinerary with cited rationale and total costPolicy controlled
5. Confirm and ticket the bookingTravellerSelected itinerary with fare rules and total price → Confirmed BookingRecord set with supplier locatorsHuman required

Technical architecture​

Technical architecture

Cosmos DB data model​

ContainerHierarchical partition keyDocumentsSearch paths
tripPlans/tenantId, /travelerProfileIdTripPlan, TravelerPreferenceProfile, InventoryOffer, LoyaltyStandingSnapshot, BookingRecord/tripIntentVectorEmbedding, /preferenceVectorEmbedding, /tripIntentVector, /preferenceVector
destinationKnowledgeLibrary/tenantId, /destinationCodeDestinationKnowledgeChunk/bodyVectorEmbedding, /bodyVector

Query contract​

QueryContainerScopePurpose
Trip planning contexttripPlanssingle-partitionRead the trip, preferences, and loyalty standing for the traveller in one partition query.
Live offer shortlisttripPlanssingle-partitionReturn only offers that are still held and inside the budget envelope.
Destination guidance retrievaldestinationKnowledgeLibrarysingle-partitionKnowledge-container query against destinationKnowledgeLibrary (partition-aligned to /tenantId + /destinationCode): retrieve seasonality, visa, and neighbourhood guidance for the destination, read as a single partition query on the destination.
Upcoming confirmed bookingstripPlanssingle-partitionShow the traveller's confirmed reservations in departure order.

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​

Azure deployment

Clone the source repository, authenticate with Azure, and run:

Set-Location accelerators/travel-hospitality/personalized-trip-concierge
az login
./Deploy.ps1 -Runtime python -Location eastus2

Change python to csharp to deploy the .NET implementation.

Explore the implementation​

Return to all accelerators