> For the complete documentation index, see [llms.txt](https://docs.layerlens.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.layerlens.ai/more-in-this-section-2/scenarios-12.md). # Travel and hospitality scenarios Five canonical scenarios where airlines, hotels, OTAs, cruise, rental car, and tour operators use Stratix evaluation to gate AI features. ## 1. Booking and itinerary assistance **Setup:** AI helps the traveler shop, build, and confirm an itinerary across air, lodging, ground transport, activities. Inputs: traveler preferences, real-time inventory, fare rules. **Why it's hard:** * Fare rules, change/cancel policies, baggage rules differ by carrier and fare class * Real-time inventory race conditions cause "best price gone" * Cross-border requirements (visas, passport validity, vaccination) shift * DOT consumer-rule violations carry per-passenger penalties **Stakes:** * DOT enforcement on misleading fare advertising; per-violation civil penalties up to \~$59K * Airline Passengers Bill of Rights state actions in CA, NY, others * IATA fare-rule enforcement on agency channels **Stratix evaluation criteria:** | Aspect | What you measure | Pattern | | ------------------------- | --------------------------------------------------- | -------------- | | Fare-rule citation | Output cites applicable fare rules | Hard rule | | Total-price disclosure | Required price elements present (DOT 14 CFR 399.84) | Hard rule | | Change/cancel accuracy | Stated rules match the actual fare-rule database | Code assertion | | Cross-border requirements | Visa / passport / health requirements current | Citation rule | | Inventory freshness | Cited inventory within threshold | Hard rule | ## 2. Customer service for disruption **Setup:** AI assists during disruption — flight cancellation, hotel overbooking, lost bag, missed connection. Surfaces options, drafts compensation offers, escalates to human. **Why it's hard:** * Disruption rules vary (Tarmac Delay Rule, EU 261, Canadian APPR, UK 261) * Compensation accuracy must match regulation, not just brand goodwill * Stranded-passenger care obligations are time-bound * Fraud-vector — bad actors trigger compensation flows **Stakes:** * DOT enforcement on Tarmac Delay Rule; up to $32K per passenger * EU 261 fixed compensation amounts (€250-€600 typical); systematic underpayment triggers state actions * Class-action exposure on systemic disruption-handling failures **Stratix evaluation criteria:** * **Regulation-citation rule** — Compensation offer cites the specific rule (DOT, EU 261, APPR) * **Care-obligation rule** — Hard rule: meals/lodging duties surfaced when applicable * **Compensation accuracy** — Code assertion: offer matches regulation minimum * **Fraud-pattern rule** — High-risk patterns route to human review * **Plain-language judge** — Communication is clear and actionable ## 3. Loyalty and personalization **Setup:** AI personalizes content and offers based on loyalty status, history, preferences. Surfaces award redemption options, drafts upgrade offers. **Why it's hard:** * Award-availability rules are notoriously complex and change without notice * Personalized pricing in regulated geographies (EU) * Senior / accessibility-related preference handling * Loyalty-program TOS enforcement vs. customer-friendly tone **Stakes:** * FTC and state UDAP scrutiny on loyalty terms * DOT enforcement on miles-based fare advertising * EU consumer-protection actions on personalized pricing **Stratix evaluation criteria:** * **Award-availability accuracy** — Code assertion against live availability * **TOS-citation rule** — Outputs reference the program TOS * **Personalized-pricing fairness** — Group fairness on offered prices * **Accessibility-preference handling** — Hard rule: stored accommodations surface in suggestions ## 4. Revenue management and dynamic pricing **Setup:** AI suggests pricing for inventory units (rooms, seats, cars). Revenue manager approves; AI does not unilaterally publish. **Why it's hard:** * DOT full-fare advertising rule * EU price-discrimination scrutiny * Hotel resort-fee transparency post-FTC 2024 rule * Surge-pricing perception risk during emergencies **Stakes:** * FTC junk-fees rule (2024) targets undisclosed mandatory fees * DOT 14 CFR 399.84 on full-fare advertising * State AG actions on emergency surge pricing (state laws cap pricing during declared emergencies) **Stratix evaluation criteria:** * **Full-price-disclosure rule** — Hard rule: all mandatory fees disclosed * **Junk-fee guardrail** — FTC 2024 rule compliance — every output flags mandatory fees up front * **Emergency-surge guardrail** — Hard rule: in declared emergencies, suggestions cap at applicable state limit * **Personalization fairness** — Group fairness on offered prices ## 5. Accessibility and accommodations **Setup:** Travel AI surfaces accessibility info — accessible rooms, wheelchair service, dietary accommodations, service-animal handling. **Why it's hard:** * ACAA (Air Carrier Access Act) for airlines + DOT enforcement * ADA Title III for hotels + state analogs * Inaccurate accessibility claims trigger litigation * Service-animal protocols vary internationally **Stakes:** * DOT ACAA enforcement actions and consent decrees * ADA Title III lawsuits — hotels are a common target * International conventions (Montreal Convention) for service-animal incidents **Stratix evaluation criteria:** * **Accessibility-claim citation rule** — Every accessibility claim cites the source * **Verified-availability rule** — Stated accessible inventory verified live * **ACAA / ADA disclosure** — Required language present * **Service-animal protocol** — Per-jurisdiction handling rule * **Plain-language judge** — Customer can act on the information ## See also * [Travel eval patterns](/more-in-this-section-2/eval-patterns-12.md) * [Travel compliance](/more-in-this-section-2/compliance-12.md) --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://docs.layerlens.ai/more-in-this-section-2/scenarios-12.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.