Use Case Intelligence RSS Search use cases Search
Google Cloud Financial Services Global

Xapien

Risk Management

Xapien needed a more accurate, multilingual due-diligence engine that could process huge amounts of unstructured global data quickly enough to avoid customer wait queues while staying affordable.

Read the original story Explore all use cases

Reported impact

Business outcome

Xapien improved report accuracy, reduced report turnaround time, and made its due-diligence service more scalable for banks and enterprises working across many languages and scripts.

  • Productivity Improvement
  • Risk Reduction
  • Scalability

Solution

Xapien uses Google Cloud to address this challenge: Xapien needed a more accurate, multilingual due-diligence engine that could process huge amounts of unstructured global data quickly enough to avoid customer wait queues while staying affordable. Gemini 2.5 Flash handles high-volume parsing tasks such as name normalization and fast report preparation, serving as the compute layer. Gemini 2.5 Pro performs the deeper reasoning needed to summarize risks and keep report accuracy high, serving as the compute layer. Google Kubernetes Engine scales the research engine globally so more simultaneous reports can run without queueing users, serving as the orchestration layer. Gemini Code Assist helps the engineering team prototype new platform capabilities in hours rather than days, serving as the serving layer.

Data flow

Unstructured multilingual source material enters the research engine, Gemini Flash handles high-volume parsing, Gemini Pro performs higher-order reasoning and risk summarization, and GKE scales report execution globally so customers receive results with less waiting.

Solution architecture

4 components · 3 layers
  1. Compute
    • Gemini 2.5 Flash handles high-volume parsing tasks such as name normalization and fast report preparation
    • Gemini 2.5 Pro performs the deeper reasoning needed to summarize risks and keep report accuracy high
  2. Serving
    • Gemini Code Assist helps the engineering team prototype new platform capabilities in hours rather than days
  3. Orchestration
    • Google Kubernetes Engine scales the research engine globally so more simultaneous reports can run without queueing users

Architecture clues

  • Gemini handles non-Latin scripts and cultural naming conventions more accurately than older NLP approaches
  • Load testing showed five times more simultaneous reports than the previous platform
  • The platform uses a multi-model architecture to balance cost, speed, and reasoning depth

Evidence from the source

For high-volume tasks, the team uses Gemini 2.5 Flash.
For the sophisticated reasoning required to summarize risks and ensure report accuracy, Xapien uses Gemini 2.5 Pro.
Xapien transformed its due-diligence platform with Google Cloud, cutting wait times and achieving 97% accuracy with Gemini models.
Transparency Evidence & methodology 70/100 reference value · 72% 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 value70/100
  • 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 impact0/25
    0 metrics describe measurable impact.
  • Deployment scale10/10
    Rewards evidence of a live or scaled deployment and meaningful integration scope.
Evidence confidence72%
  • 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 evidence15/20
    3 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

    Xapien customer story

    First-party
    https://cloud.google.com/customers/xapien
    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 Apr 3, 2026 · 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 Mar 25, 2026 · Google Cloud · 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
Google Cloud Modified · Oct 9, 2026 Policybazaar Financial Services India Motor insurance options in India can be complex, which is why Policybazaar built its market-leading reputation by making the consumer journey entirely transparent and accessible. The digital platform empowers millions… Achieved 97% issuance within five minutes in PAYD using Gemini models Document ProcessingRisk Management Cloud Storage · Gemini 2.5 Flash · Gemini 2.5 Flash-Lite Google Cloud Archived · Sep 17, 2026 Home Credit Bank Financial Services Kazakhstan Home Credit Bank needed a safer enterprise AI environment that non-technical teams could use to build banking agents quickly without creating data-leak risk or relying on a long custom-development cycle for each new use… Achieved 100% migration to a secure AI environment Customer Service AutomationEnterprise Knowledge Search Agent Designer · Gemini Enterprise Google Cloud Modified · Aug 28, 2026 PvX Partners Financial Services Singapore The PvX team needed a way to ingest and normalize the data into a single model while staying aligned with strict compliance standards from the Monetary Authority of Singapore (MAS). The platform also had to scale to… Committed $1B+ of financing to gaming and consumer app companies Risk Management BigQuery · Cloud Run · Cloud SQL