Travel & Hospitality

Disruption Recovery Assistant

Designed for Traveler or operations agent

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.

Contract TRV-02 · primary aggregate DisruptionCase · mode loading

Decision brief

Accept and issue the recovery: 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

Traveller or operations agent

The named role remains accountable for the consequential decision.

Governed evidence

5 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 cancelled evening transatlantic flight strands 214 passengers; the assistant ranks 38 travellers with missed onward connections first, generates policy-compliant rerouting through two hubs plus 96 hotel rooms, messages each traveller in their preferred language with their compensation entitlement, and reissues tickets only as each option is accepted..

Decision to make

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.

Outcome to show

Reissued ticket, hotel voucher, and updated itinerary gives Traveller or operations agent the evidence needed to begin the final governed business outcome, with the decision trail retained for review.

  1. 1Declare the disruption and scope impact
  2. 2Prioritize travellers by risk and entitlement
  3. 3Generate feasible re-accommodation options
  4. 4Communicate options in the traveller's language
  5. 5Accept and issue the recovery

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

Traveller or operations agent 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 DisruptionCase 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
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.
Primary aggregate
DisruptionCase
Primary container
disruptionCases
Hierarchical key
/tenantId + /disruptionEventId
Schema version
1

Sample scenario

A cancelled evening transatlantic flight strands 214 passengers; the assistant ranks 38 travellers with missed onward connections first, generates policy-compliant rerouting through two hubs plus 96 hotel rooms, messages each traveller in their preferred language with their compensation entitlement, and reissues tickets only as each option is accepted.

Physical Cosmos DB containers

Every container provisioned for this accelerator with its hierarchical partition key.
Container Role Hierarchical partition key Document types
disruptionCases Primary /tenantId + /disruptionEventId DisruptionCase, AffectedItinerary, ReaccommodationOption, TravelerCommunication
entitlementPolicyLibrary Reference /tenantId + /jurisdiction PolicyRule

Document types

Contract document types, their owning container, and their identifier pattern.
Type Container Partition key Identifier pattern Embedding fields
DisruptionCase disruptionCases /tenantId + /disruptionEventId disruption::{disruptionEventId} None
AffectedItinerary disruptionCases /tenantId + /disruptionEventId itinerary::{disruptionEventId}::{recordLocator} None
ReaccommodationOption disruptionCases /tenantId + /disruptionEventId option::{disruptionEventId}::{recordLocator}::{optionId} None
PolicyRule entitlementPolicyLibrary /tenantId + /jurisdiction policy::{jurisdiction}::{policyId}::{clauseIndex} clauseVector
TravelerCommunication disruptionCases /tenantId + /disruptionEventId communication::{disruptionEventId}::{messageId} None

Query patterns