Enterprise Knowledge Search · Sales Automation
BBVA needed to reduce the time employees spent searching dispersed legal and operational documentation, speed up marketing content creation, help staff find relevant data in its enterprise data model, and improve software development productivity across the group.
Reported impact
BBVA reports faster legal response preparation, higher-quality first responses, shorter marketing content creation cycles, improved ad visibility and clicks, faster data discovery, and better developer productivity through task-specific generative AI assistants.
BBVA deployed ChatGPT Enterprise at group scale and used it to build customized GPTs for specific internal workflows. In the legal function, BBVA loaded consultation documents, product specification sheets, and internal and external regulations into a GPT so lawyers could retrieve relevant guidance faster and draft fuller answers before a human review step. In marketing, BBVA configured another GPT with instructions, contextual documents, and examples of prior high-performing campaign text so it could generate search-optimized ad copy. For data governance, BBVA connected a GPT-driven conversational interface to its Single Data Model so employees could find data types, identify data owners, and see where data had already been used in other applications. BBVA also created an internal GPT Store to publish reusable assistants, while developers used ChatGPT and GitHub Copilot for coding, documentation, and code translation tasks.
BBVA feeds legal reference material, regulations, campaign instructions, contextual documents, and prior campaign text into task-specific GPTs running in ChatGPT Enterprise. For data discovery, the GPT interface helps employees navigate metadata and usage information in the Single Data Model. Outputs are then consumed by lawyers, marketers, data users, and developers, with reusable assistants distributed through BBVA's internal GPT Store.
"All responses undergo a human review before being sent to the branch managers."
"The Group operates a Single Data Model, in which it centralizes all the information related to all its departments and operations"
"The bank’s software developers are starting to rely on ChatGPT and other tools such as GitHub Copilot"
"The mass deployment of more than 3,000 ChatGPT Enterprise licenses across the BBVA Group has unleashed a wave of innovative ideas"
"a GPT that helps write creative copy for advertising campaigns has succeeded in reducing the time it takes to create and develop these actions."
"a task that used to take hours can now be completed in a matter of minutes."
"made ads more effective by almost doubling the number of times they appear in search engines."
"the advisory legal team has created a GPT... containing all the consultation documents"
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
Related
Baidu AI Cloud Sample May 14, 2025 Taikang Insurance Group Co., Ltd. Taikang needed to unify and activate large volumes of scattered enterprise knowledge so employees and insurance agents could retrieve the right information quickly, train against realistic scenarios, and serve customers… Internal operational knowledge retrieval became 80% faster. AI Zhixun Performer Edition · Financial Zhihui Platform · Hui Operations Assistant 
In-house Sample Apr 8, 2025 Bank of America Bank of America needed to improve employee productivity and client service at scale across a global workforce of 213,000 people, while reducing routine support demand, accelerating employee access to information,… 20 million clients now actively using the virtual assistant Erica · Erica for Employees · PRIVATE BANK 
LangChain Sample Feb 27, 2025 MUFG Bank MUFG Bank’s FX and derivative sales teams spent too much time reading annual reports, market data, and financial disclosures by hand before they could create tailored presentations and recommendations for corporate… 100-200 pages Next.js · Python version of LangChain · Retriever interface 
