Use Case Intelligence RSS Search use cases Search
Google Cloud Travel and Hospitality India

Yatra

Document Processing

Reconciling fragmented receipts across global jurisdictions was a substantial manual task, with throughput often limited by the sheer volume and variability of the data.

Read the original story Explore all use cases
As a trusted corporate travel provider, Yatra manages the end-to-end travel requirements for over 6,000 corporate customers. Historically, expense management was a high-touch process defined by significant operational overhead. Reconciling…
Automated expense logs for 6,000+ firms through Google Gemini
Beyond operational gains, Yatra’s strategic move to was rooted in a long-term vision of data sovereignty and autonomous innovation. This transition began with a comprehensive infrastructure migration, where Yatra collaborated with Niveus…
Engineering collaboration with also focused on performance optimization, reducing receipt scanning latency from 20 seconds to a range of 3 to 4 seconds. This combination of speed and reasoning has allowed Yatra to evolve from a traditional…

Reported impact

Business outcome

Reduced scanning latency to 3-4s with Vision AI; Automated expense logs for 6,000+ firms through Google Gemini; Boosted booking intent accuracy using Gemini on Gemini Enterprise Agent Platform

  • Compliance
  • Customer Experience
  • Productivity Improvement
  • Risk Reduction

Solution

Reconciling fragmented receipts across global jurisdictions was a substantial manual task, with throughput often limited by the sheer volume and variability of the data. Shifted team to strategic ML projects on Compute Engine The transition to the 3.0 architecture within Gemini Enterprise Agent Platform (formerly Vertex AI) provided the necessary precision. DIYA can now process complex, non-linear queries, such as planning a multi-city international itinerary while accounting for… Key components include Gemini Enterprise Agent Platform coordinates multi-agent workflows, tool calling, and governed automation across the application; Vertex AI provides the reasoning or generation layer used for classification, orchestration, content generation, or analysis; Compute Engine runs serverless or virtualized application services with elastic scale for production AI workloads. Reported outcomes include Reduced scanning latency to 3-4s with Vision AI; Automated expense logs for 6,000+ firms.

Solution architecture

3 components · 2 layers
  1. Compute
    • Vertex AI Provides the reasoning or generation layer used for classification, orchestration, content generation, or analysis.
    • Compute Engine Runs serverless or virtualized application services with elastic scale for production AI workloads.
  2. Orchestration
    • Gemini Enterprise Agent Platform Coordinates multi-agent workflows, tool calling, and governed automation across the application.

Architecture clues

  • As a trusted corporate travel provider, Yatra manages the end-to-end travel requirements for over 6,000 corporate customers. Historically, expense management was a high-touch process defined by significant operational…
  • Beyond operational gains, Yatra’s strategic move to was rooted in a long-term vision of data sovereignty and autonomous innovation. This transition began with a comprehensive infrastructure migration, where Yatra…
  • By integrating multimodal capabilities like verbal expense logging and seamless “one-click” activity reservations, Yatra is removing the traditional boundaries between planning, booking, and post-trip reporting. The…
  • To address this, Yatra developed RECAP, an expense management solution built on . The objective was to implement a system capable of advanced reasoning beyond simple character recognition. By integrating the , Yatra…
  • Yatra leverages Google Cloud’s AI ecosystem to deliver autonomous travel assistants and real-time expense automation for global corporate travelers.

Evidence from the source

As a trusted corporate travel provider, Yatra manages the end-to-end travel requirements for over 6,000 corporate customers. Historically, expense management was a high-touch process defined by significant operational…
Boosted booking intent accuracy using Gemini on Gemini Enterprise Agent Platform
Reduced scanning latency to 3-4s with Vision AI
Shifted team to strategic ML projects on Compute Engine
The transition to the 3.0 architecture within Gemini Enterprise Agent Platform (formerly Vertex AI) provided the necessary precision. DIYA can now process complex, non-linear queries, such as planning a multi-city…
To address this, Yatra developed RECAP, an expense management solution built on . The objective was to implement a system capable of advanced reasoning beyond simple character recognition. By integrating the , Yatra…
Transparency Evidence & methodology 95/100 reference value · 77% 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 value95/100
  • Problem clarity20/20
    Measures whether the customer's operational problem is specific enough to compare.
  • Implementation depth20/25
    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 confidence77%
  • 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
    6 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 specificity8/10
    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. Google Cloud

    Yatra customer story

    First-party
    https://cloud.google.com/customers/yatra
    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

  • Sitemap last modified Jun 9, 2026 · Google Cloud · Publisher metadata Publisher-reported modification timestamp; not a publication date.
    Open date source
  • Unverified extracted date Jun 9, 2026 · Google Cloud · Unknown Legacy extracted date without source-page confirmation.
    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
Google Cloud Archived · Apr 28, 2026 Thrive Restaurant Group Travel and Hospitality United States However, rapid growth through acquisitions created a complex technological environment. With nearly 30 disparate systems and more than 200 restaurants across various time zones, teams were spending more time manually… Accelerated time to insights from three hours to 30 seconds with LookML Data Lake / Data Warehouse ModernizationDocument Processing BigQuery · Gemini · Gemini Enterprise Google Cloud Archived · Mar 26, 2026 Wego Travel and Hospitality Singapore Wego transitioned from fragmented, inconsistent data silos to a unified analytical framework using Google Cloud and Looker. By leveraging Looker's semantic layer, Wego has democratized data access for all departments,… Document ProcessingReal-time Analytics BigQuery · LookML · Looker Google Cloud Archived · Oct 9, 2026 Angelus Healthcare Brazil Founded by a dentist whose first product was based on a patent, Angelus competes on differentiation, developing bioceramic products and fiberglass post lines that require clinical proof, intellectual property… 50,000 pages of proprietary data now powering AI-generated documents Document Processing Gemini