Skip to main content
TRV-02 · Travel & Hospitality

Disruption Recovery Assistant

Outcome​

Recover travellers from cancellations and delays quickly by matching disrupted itineraries to feasible re-accommodation options within fare rules, duty-of-care policy, and available inventory, with an agent or traveller accepting the option before it is issued.

Portfolio attributeValue
Primary personaTraveler or operations agent
Primary aggregateDisruptionCase
Cosmos DB containers2
Grounding dataflight operations, airport events, PSS/GDS reservations and inventory, minimum connection times, baggage state, fare rules, passenger-rights policy, loyalty priority, contact-center history, hotel rail and ground partners
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
ProductivityDisruption-to-protected-itinerary time15-30% reduction(baseline median disruption-to-protection minutes - assisted median minutes) / baseline median minutes * 100
Quality or riskEntitlement and option correctness5-10 percentage-point improvementassisted percentage meeting the entitlement and feasible-option rubric - baseline percentage
Business outcomeRecovery cost per disrupted traveler5-10% reduction(baseline recovery cost per disrupted traveler - assisted cost) / baseline cost * 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: Flight, booking, entitlement, inventory, and partner evidence supports faster recovery ranking and a cautious cost hypothesis.

Pilot guardrail: Travelers or operations controllers approve options before issuance; compare equivalent disruption classes.

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 disruption-to-protected-itinerary time and entitlement and option correctness 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. Declare the disruption and scope impactOperations controlCancellation or major delay notification → DisruptionCase with affected itinerariesPolicy controlled
2. Prioritize travellers by risk and entitlementPrioritization agentConnections at risk, vulnerability, and loyalty tier → Ranked recovery queuePolicy controlled
3. Generate feasible re-accommodation optionsRecovery agentLive inventory, fare rules, and duty-of-care policy → ReaccommodationOption set with compliance flagsPolicy controlled
4. Communicate options in the traveller's languageDisruption assistantRanked options and traveller contact preferences → Clear multilingual offer with entitlements statedPolicy controlled
5. Accept and issue the recoveryTraveller or operations agentChosen option with cost and arrival impact → Reissued ticket, hotel voucher, and updated itineraryHuman required

Technical architecture​

Technical architecture

Cosmos DB data model​

ContainerHierarchical partition keyDocumentsSearch paths
disruptionCases/tenantId, /disruptionEventIdDisruptionCase, AffectedItinerary, ReaccommodationOption, TravelerCommunicationOperational fields only
entitlementPolicyLibrary/tenantId, /jurisdictionPolicyRule/clauseVectorEmbedding, /clauseVector

Query contract​

QueryContainerScopePurpose
Disruption recovery queuedisruptionCasessingle-partitionRead affected itineraries and their options for the event in one partition query.
Missed-connection risk listdisruptionCasessingle-partitionPrioritize travellers whose onward connections will be missed.
Policy-compliant option filterdisruptionCasessingle-partitionKeep only options permitted by fare rules and duty-of-care policy.
Jurisdiction entitlement lookupentitlementPolicyLibrarysingle-partitionKnowledge-container query against entitlementPolicyLibrary (partition-aligned to /tenantId + /jurisdiction): return the compensation and care entitlements that apply to the affected journeys, read as a single partition query on the governing jurisdiction.

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/disruption-recovery-assistant
az login
./Deploy.ps1 -Runtime python -Location eastus2

Change python to csharp to deploy the .NET implementation.

Explore the implementation​

Return to all accelerators