Use Case Intelligence RSS Search use cases Search
Snowflake Travel and Hospitality Hanover, Germany

TUI Group

Enterprise Knowledge Search · Real-time Analytics

Decentralized business-unit data practices and complex analytics tooling made it hard for nontechnical users to discover the right data, understand schemas, and get answers quickly.

Read the original story Explore all use cases
1 hour to develop its first AI use case
30+ days potentially saved per year
over 500 complex data queries were answered in natural language

Reported impact

Business outcome

TUI built AI data-discovery prototypes in hours, answered more than 500 complex natural-language queries during early testing, and expects each use case to save more than 30 days of people time while improving data quality and responsiveness.

  • Customer Experience
  • Productivity Improvement
  • Speed to Market

Solution

TUI standardized enterprise analytics on Snowflake so governed travel, customer, and operational data could support both classic reporting and new AI-driven discovery workflows. The Technology Analytics team runs Snowflake on AWS as the backbone for data across airlines, hotels, agencies, cruises, and internal business functions. On top of that foundation, TUI built TACO, an AI assistant powered by Cortex Analyst that uses semantic models to let users ask natural-language questions against approved schemas. In parallel, Cortex Search indexes enterprise metadata so employees can locate data products, understand who owns them, and discover where key data sits without manually digging through separate tools. The same indexing work also surfaced data-quality issues that TUI fixed as part of rollout. By keeping core data, semantic modeling, metadata search, and user-facing AI on one governed platform, TUI improved self-service access while reducing demand on central data teams.

Data flow

Business-unit data is centralized in Snowflake on AWS. Cortex Analyst uses semantic models on top of governed schemas to answer natural-language questions, while Cortex Search indexes metadata so employees can find datasets, owners, and data products through TUI's discovery interfaces.

Solution architecture

3 components · 3 layers
  1. Compute
    • Cortex Analyst Powers TACO so users can query business data in natural language through semantic models.
  2. Storage
    • Snowflake Provides the unified enterprise data platform that stores and governs travel, customer, and operational datasets.
  3. Serving
    • Cortex Search Indexes metadata and data-product context so users can discover datasets and owners more easily.

Architecture clues

  • Cortex Search indexes enterprise metadata for discovery across business units.
  • TACO uses Cortex Analyst with semantic models built from TUI schemas.
  • The team is extending the design into a semantic catalog over the metadata store.

Evidence from the source

Cortex AI now powers TUI's Technology Analytics Companion (TACO), an AI platform powered by Cortex Analyst that allows users to query data through natural language.
Using Cortex Search, TUI has been able to index all its metadata, making it searchable and discoverable for everyone in the business.
over 500 complex data queries were answered in natural language
save over 30 days-or even months-of people hours
within an hour of tweaking I was getting answers
Transparency Evidence & methodology 100/100 reference value · 79% confidence · 1 source

Review how this reference was scored and trace each normalized claim back to its documented source.

01

Scoring methodology

How scores are calculated

Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.

Customer reference value100/100
  • Problem clarity20/20
    Measures whether the customer's operational problem is specific enough to compare.
  • Implementation depth25/25
    Rewards named components, data flow, integrations, and architecture detail.
  • Outcome specificity20/20
    Measures whether the reported benefit is concrete rather than a generic claim.
  • Quantified impact25/25
    2 metrics describe measurable impact.
  • Deployment scale10/10
    Rewards evidence of a live or scaled deployment and meaningful integration scope.
Evidence confidence79%
  • Source authority20/25
    The main evidence is an official vendor-published customer story.
  • Claim traceability21/25
    10 of 12 key fields link to a named source.
  • Direct evidence20/20
    5 direct source quotes retained.
  • Date provenance0/10
    The publication date has no documented provenance.
  • Source transparency8/10
    1 source reference document publisher, URL, authority, retrieval, and supported fields.
  • Implementation specificity10/10
    Rewards source-backed components, data flow, quantified impact, and a specific outcome.
02

Traceability

Sources & provenance

Field coverage shows which facts each source supports. Dates are shown only when documented by the source.

  1. Snowflake

    TUI Group customer story

    First-party
    https://www.snowflake.com/en/customers/all-customers/case-study/tui/
    Source type
    Vendor-published customer story
    Supports
    • Customer
    • Business problem
    • Solution
    • Products
    • Solution components
    • Data flow
    • Integrations
    • technical area
    • use case category
    • Business outcome
    • outcome category
    • Metrics
    • Architecture
    • evidence quotes

Date evidence

  • First archived Sep 16, 2025 · Internet Archive · Independent First Wayback Machine capture; confirms the page existed by this date, not when it was published.
    Open date source
  • Sitemap last modified Jul 9, 2026 · Snowflake · Publisher metadata Publisher-reported modification timestamp; not a publication date.
    Open date source
Not separately sourced Industry, Region, Company size. Treat these normalized attributes as lower-confidence until a dedicated source is added.

Related

Similar use cases

See all like this
Snowflake Archived · Sep 2, 2026 Under Armour Retail Global Fragmented systems, workbook-driven reporting, and inconsistent definitions kept planners and executives from getting fast, trusted answers, making it hard to keep pace with rapid retail decisions and emerging AI demand. A week to produce. Enterprise Knowledge SearchReal-time Analytics Data Clean Rooms · Secure Data Sharing · Snowflake Databricks Jul 8, 2026 Eurowings Travel and Hospitality Germany Before unifying its data strategy, Eurowings faced significant challenges with siloed data across disparate systems. Technical barriers in vector storage also slowed development, as the team had to manually manage… By implementing semantic search powered by Databricks AI Search and Model Serving, Eurowings achieved a 109%… Data Lake / Data Warehouse ModernizationEnterprise Knowledge Search Agent Bricks · Databricks AI Search · MLflow Snowflake Archived · Sep 1, 2025 RavenPack Financial Services Marbella, Spain and New York, USA Delivering multi-petabyte financial data to clients across regions and clouds through FTP and ETL pipelines was too slow, siloed, and expensive for RavenPack's growing analytics and AI business. 14x lower egress costs Enterprise Knowledge SearchReal-time Analytics AWS Bedrock · Bigdata.com · Egress Cost Optimizer