In-house Financial Services global Company newsroom

Bank of America

Enterprise Knowledge Search

Global Payments Solutions employees needed too long to answer complex client product and onboarding questions because knowledge was spread across internal materials and often required calls with product specialists in different regions and time zones.

a sophisticated inquiry could take an employee an hour to complete
more than 40,000 business clients worldwide
over 3,200 internal documents and presentations
save tens of thousands of hours annually

Reported impact

Business outcome

Bank of America expects the assistant to save tens of thousands of employee hours annually while speeding product and onboarding responses, enabling more tailored client solutions, and improving strategic advisory support.

  • Customer Experience
  • Productivity Improvement

Solution

Bank of America built Ask Global Payments Solutions (AskGPS) in-house as a generative AI assistant for its Global Payments Solutions organization. The implementation is centered on a curated internal knowledge corpus: over 3,200 internal documents and presentations, including product guides, term sheets, and FAQs, are used to train the assistant and turn static reference content into a real-time question-answering system. Employees can submit simple or complex client questions and receive responses within seconds, rather than manually searching documents or contacting regional product specialists. The assistant serves salespeople and bankers by surfacing vetted answers, best practices, and precedents across sectors and geographies to support product, onboarding, and advisory conversations. The source does not name an external model provider, storage platform, or orchestration stack, so the disclosed architecture is limited to the in-house GenAI application layer and its internal document corpus.

Data flow

Internal documents and presentations, including product guides, term sheets, and FAQs, are used to train Ask Global Payments Solutions. The in-house generative AI assistant processes employee questions against this vetted knowledge base and returns near-instant answers, best practices, and precedents to Global Payments Solutions staff for client product, onboarding, and advisory work.

Solution architecture

1 components · 1 layer
  1. Serving
    • Ask Global Payments Solutions (AskGPS) An in-house generative AI assistant that answers employee questions using vetted internal payments knowledge.

Architecture clues

  • Built in-house by Bank of America
  • Source does not disclose the model provider, storage layer, or deployment topology
  • Supports the Global Payments Solutions team serving more than 40,000 business clients worldwide
  • Trained on over 3,200 internal documents and presentations

Evidence from the source

"Now, using [AskGPS], employees can achieve the same result almost instantly, creating the potential to save tens of thousands of hours annually."
"Previously, a sophisticated inquiry could take an employee an hour to complete and involve making phone calls to product specialists across different regions and time zones."
"The assistant directly benefits Bank of America clients through: Faster turnaround on product and onboarding inquiries"
"The newly launched Ask Global Payments Solutions ... was built in-house and trained on over 3,200 internal documents and presentations – including product guides, term sheets, and FAQs."
"employees can now pose simple to complex client questions and receive answers within seconds."
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. Bank of America

    Bank of America customer story

    First-party
    https://newsroom.bankofamerica.com//content/newsroom/press-releases/2025/09/bofa-s-new-genai-assistant-transforms-global-payments-solutions.html
    Source type
    Customer-published story
    Published
    Sep 30, 2025
    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 Sep 30, 2025 · Bank of America · 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.