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

Embat

Document Processing · IT Operations Automation

Embat needed to automate complex reconciliation and treasury workflows for finance teams, reduce manual intervention and accounting errors, and keep adding advanced automation capabilities without building a custom training dataset for each customer scenario.

Read the original story Explore all use cases
32.7% of the dataset for automatic reconciliation processes
Enriching almost one third (33%) of the dataset for automatic reconciliation processes
automate all cases that would require user intervention (5%)
eliminate the -minimal- errors that were still being produced by automated suggestions (2.2%)

Reported impact

Business outcome

Embat reduced manual finance work, eliminated residual automated-suggestion errors, and turned Google Cloud-based generative AI into a competitive differentiator for treasury automation in the Spanish fintech market.

  • Cost Reduction
  • Productivity Improvement
  • Speed to Market

Solution

Embat built its treasury-automation platform on Google Cloud and used Vertex AI generative AI to improve the most complex reconciliation and accounting tasks. The fintech runs its hosting, microservices architecture, databases, analytics, and ERP integrations on Google Cloud, then uses Vertex AI to break complex tasks into simpler subtasks and enrich transaction data before it reaches the reconciliation engine. That enrichment layer extracts more useful context from receipts and payments, reduces unnecessary data, and generates more accurate settlement suggestions for customers without requiring a bespoke training corpus. The resulting platform automates cases that previously required human intervention and feeds its outputs into an automatic accounting workflow that produces daily receipt and payment logs. Embat is extending the same foundation with Gemini for Google Workspace and additional automation experiments as it expands the product.

Data flow

Payment and receipt data flows through Embat's Google Cloud microservices and external ERP integrations into Vertex AI, which enriches and classifies the records for automatic reconciliation. The enriched outputs feed Embat's settlement proposal engine and daily accounting logs, which finance teams review and act on.

Solution architecture

2 components · 2 layers
  1. Compute
    • Vertex AI Runs the generative AI workflows that enrich reconciliation data, break complex tasks into subtasks, and improve automatic settlement suggestions.
  2. Serving
    • Gemini for Google Workspace Extends Embat's Google Cloud-based automation foundation into employee productivity and future finance workflows.

Architecture clues

  • External APIs integrate Embat with ERP systems, analytics, and databases
  • The entire Embat solution is based on products from Google Cloud
  • The platform uses a microservices architecture
  • Vertex AI generative AI is used without a customer-specific training dataset

Evidence from the source

The solution lay in Vertex AI Generative Artificial Intelligence, the large language model (LLM) from Google Cloud capable of breaking down a complex task into simpler sub-tasks.
Today, the entire Embat solution is based on products from Google Cloud: the hosting, the microservices architecture, the external APIs for integrations with ERP, analytics and the database.
helped to enrich almost one third (32.7%) of the dataset for automatic reconciliation processes
implementation of the Generative AI of Vertex AI enabled Embat to automate all cases that would require user intervention (5%)
saving up to 10 hours per week and reducing accounting errors.
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
    7 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. Google Cloud

    Embat customer story

    First-party
    https://cloud.google.com/customers/embat-ai
    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 8, 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 Apr 1, 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 Anthropic Software / SaaS San Francisco, CA, USA During large-scale training runs, traffic is highly variable—dropping to near zero during model checkpointing before bursting to millions of events per minute. Anthropic needed a serverless messaging queue that scaled… Handles peak throughput of over 1M events per second Document ProcessingIT Operations Automation BigQuery · Bigtable · Cloud Pub/Sub Google Cloud Archived · Oct 9, 2026 CBRE Real Estate and Construction United States As the world's largest commercial real estate services and investment firm, CBRE delivers a fully integrated suite of financial, property accounting, and fund administration services. Managing asset-level transactional… CBRE is leveraging the Gemini platform with the help of McKinsey to rapidly build, deploy, and scale… Document ProcessingIT Operations Automation Agent Development Kit (ADK) · Gemini platform Google Cloud Modified · Oct 9, 2026 Porter Logistics India Porter (Smartshift Logistics Private Limited), a leading logistics platform based in India, orchestrates on-demand mini-trucks, tempos, and two-wheelers across 50+ major cities. When order volumes doubled, Porter’s… Achieved 30% zero-touch driver verification automation on Gemini platform Application RefactoringDocument Processing BigQuery · Cloud Composer · Cloud Pub/Sub