Use Case Intelligence RSS Search use cases Search
In-house Financial Services Global Company newsroom

PayPal

Enterprise Knowledge Search · Real-time Analytics

PayPal needed to give employees conversational access to company data at enterprise scale without requiring SQL, dashboards, or intermediary engineering teams, while still meeting strict security and compliance requirements.

Read the original story Explore all use cases
answers in minutes instead of hours
hundreds of millions of consumers and merchants
thousands of employees

Reported impact

Business outcome

PayPal says the agent enables self-service analytics for thousands of employees, cuts time-to-insight from hours to minutes, reduces dependence on engineering support, and frees engineering teams to focus on new commerce experiences.

  • Customer Experience
  • Productivity Improvement
  • Risk Reduction

Solution

PayPal describes a multi-year effort to unify data systems across the company and create a real-time, AI-ready foundation that could support applied AI use cases. On top of that foundation, PayPal deployed an AI-powered internal agent that lets employees ask natural-language questions about data instead of writing SQL or waiting for specialists. The page says the implementation connects systems to enable real-time data access and references governed conversational analytics with Looker and MCP. PayPal's engineering teams built a custom architecture around the experience so credentials remain encrypted and every interaction is audited, allowing the system to satisfy rigorous security and compliance requirements while still serving self-service analytics. In practice, the stack turns a centralized data platform into a governed serving layer for thousands of employees and supports faster internal decisions, with adjacent impact mentioned for false declines, fraud detection, and customer experience improvements.

Data flow

Data from PayPal's previously separate internal systems is unified into a real-time data foundation. Employees submit natural-language questions to an AI-powered agent, which accesses the governed analytics layer referenced with Looker and MCP. PayPal's custom architecture keeps credentials encrypted, audits each interaction, and returns answers directly to users without requiring SQL, dashboards, or engineering intermediaries.

Solution architecture

2 components · 2 layers
  1. Serving
    • Looker Referenced as part of PayPal's governed conversational analytics capability used to answer employees' natural-language data questions.
  2. Orchestration
    • MCP Referenced as part of the architecture used to connect the conversational analytics experience to governed data access.

Architecture clues

  • Custom architecture keeps credentials encrypted.
  • Designed for self-service use by thousands of employees.
  • Interactions are audited to meet security and compliance standards.
  • Multi-year initiative to unify data systems across PayPal.
  • Real-time, AI-ready data foundation.

Evidence from the source

"PayPal has deployed an AI-powered agent that allows thousands of employees—from data scientists to customer success managers—to query data using natural language."
"PayPal leaders shared how they are deploying agentic AI across both customer-facing commerce and internal operations"
"PayPal’s engineering teams developed a custom architecture that keeps credentials encrypted and ensures interactions are audited"
"Read more: PayPal secures and scales governed conversational analytics with Looker, MCP"
"There’s no need for SQL, dashboards, or intermediary teams—employees can get answers in minutes instead of hours."
Transparency Evidence & methodology 75/100 reference value · 92% 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 value75/100
  • 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 impact0/25
    0 metrics describe measurable impact.
  • Deployment scale10/10
    Rewards evidence of a live or scaled deployment and meaningful integration scope.
Evidence confidence92%
  • Source authority25/25
    The deployment is described by the adopting organization or a government source.
  • Claim traceability21/25
    10 of 12 key fields link to a named source.
  • Direct evidence20/20
    5 direct source quotes retained.
  • Date provenance10/10
    The publication date comes from the source page or publisher.
  • 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. PayPal

    PayPal customer story

    First-party
    https://newsroom.paypal-corp.com/2026-04-23-PayPal-Showcases-AI-Powered-Innovation-at-Google-Cloud-Next-26-Built-on-the-Foundation-of-One-of-the-Largest-Data-Migrations-in-History
    Source type
    Customer-published story
    Published
    Apr 23, 2026
    Supports
    • Customer
    • Business problem
    • Solution
    • Products
    • Solution components
    • Data flow
    • Integrations
    • technical area
    • use case category
    • Business outcome
    • outcome category
    • Metrics
    • Architecture
    • evidence quotes
    • Publication date

Date evidence

  • Published on source page Apr 23, 2026 · PayPal · First-party
    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 · Jun 18, 2026 HiPay Financial Services France HiPay needed to replace a legacy BI environment that was causing dashboard fatigue, low self-service adoption, and duplicated calculations, while still preserving strong metric governance and security for payment… drives 50% higher BI adoption Enterprise Knowledge SearchReal-time Analytics BigQuery · Gemini Enterprise Agent Platform · Looker Google Cloud Archived · Apr 22, 2026 PayPal Financial Services United States PayPal wanted thousands of employees to query petabytes of governed finance data conversationally, but it had to avoid plaintext secrets, AI hallucinations, inconsistent metric definitions, and data-loss-prevention… Achieved near 100% accuracy in AI-generated insights Enterprise Knowledge SearchReal-time Analytics BigQuery · Claude · Looker 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