EY puts Elasticsearch at the heart of generative AI platform for banks

Title

EY puts Elasticsearch at the heart of generative AI platform for banks

Content

EY, one of the largest professional services networks in the world and a leading provider of solutions to the financial sector, built its generative AI platform on Elasticsearch to unlock insights from vast quantities of unstructured data — ESG reports, financial statements and multi-table documents — for its banking clients. The platform helps banks streamline regulatory reporting, extract structured fields from long documents, and compare information across reports from different years. "With ESRE, we can use machine learning models to generate vector embeddings stored at large scale. We used the super-efficient embedding model to build out the RAG component, which significantly reduced our processing time." — Vishaal Venkatesh, GenAI Manager, EY. "Elastic's cutting-edge work in search and retrieval attracted us," Venkatesh adds, explaining why EY selected ESRE as the foundation of its RAG architecture. "Our primary focus is to champion responsible AI and deliver these solutions effectively to our clients," Venkatesh notes. The platform targets two strategically valuable areas: ESG and financial reports. "Elastic allows us to help banks streamline reporting on their ESG commitments, including internal metrics and details from the full value chain," Venkatesh says. For financial reports, EY's solution extracts data and insights from complex documents with numerous tables. "Imagine extracting 14 key variables from a 40-page PDF or comparing information across multiple reports from different years. This is where we save clients significant time and resources," Venkatesh notes. Technical architecture: Elasticsearch Relevance Engine (ESRE) provides machine-learning models, a vector database and advanced search/retrieval at the core; LlamaIndex connects LLMs to external data sources; LangChain orchestrates RAG; LanceDB serves as an open-source vector database option. EY also used enhanced indexing and chunking from the Elastic product suite, which significantly reduced RAG processing time. Operationally, the deployment delivers faster document-understanding across ESG and financial-statement workflows, removes the need to build and maintain homegrown retrieval infrastructure, and gives EY banking clients a production-grade path to responsible generative AI. "With Elastic, we can simultaneously promote responsible AI and innovation. It means our clients can adhere to regulations, act faster, and mitigate internal risks," Venkatesh says. EY, headquartered in London, operates across audit, tax, consulting and advisory services globally. The platform is positioned as long-term infrastructure for EY's financial-services AI delivery. Source: Elastic customer story, elastic.co/customers/ey, 2026.