S&P Global Unveils Adaptive Retrieval: A New Era for Data Access in Financial Services

Adaptive Retrieval allows AI agents and large language models (LLMs) to seamlessly access and assemble data from various licensed sources using natural language queries. This functionality is complemented by S&P Global's existing Deterministic Retrieval method, which has been operational since 2025 and is built on the Kensho LLM-ready API. Together, these two retrieval methods are now available through the S&P Global AI Data Portal, providing customers with diverse options tailored to their specific operational needs.

The introduction of Adaptive Retrieval is particularly significant for organizations engaged in complex, multi-step tasks such as in-depth research and report generation. By enabling AI agents and LLMs to pull data from multiple datasets simultaneously, this new service eliminates the cumbersome manual processes traditionally involved in data retrieval. In contrast, Deterministic Retrieval is designed for more focused tasks, allowing users to conduct targeted research, such as analyzing earnings call transcripts or specific company data.

Sally Moore, Chief Client Officer and Co-Head of Market Intelligence at S&P Global, emphasized the rapid evolution of AI in financial services. "The use of AI in financial services is rapidly accelerating and evolving, from tightly controlled workflows to fully autonomous, multi-agent systems," she noted. With both retrieval methods now accessible, S&P Global aims to ensure that its trusted data is available across the full spectrum of workflows, adapting to the changing needs of customers as their architectures evolve.

As businesses transition from human-driven processes to AI-driven workflows, the demand for high-quality, verifiable, and auditable data has surged. Historically, integrating reliable data into AI systems required substantial engineering efforts, including sourcing validation and constructing retrieval logic. Adaptive and Deterministic Retrieval simplify this process, providing customers with structured, cited data ready for immediate use in AI applications. This allows organizations to concentrate on generating insights and developing innovative products rather than managing data logistics.

The launch of Adaptive Retrieval follows S&P Global's recent evolution of its Market Intelligence operating model, which integrates data, AI, software, and workflow capabilities to enhance customer intelligence discovery and consumption. This initiative reflects the newly established Kensho Data Platforms vertical's commitment to delivering world-class client interfaces, such as Capital IQ Pro, thereby facilitating AI-native user experiences.

Bhavesh Dayalji, Head of Kensho Data & Intelligence, remarked, "For S&P Global, the data retrieval layer is only the beginning. Cited, verifiable S&P Global data provides the trusted foundation on which higher-value AI-native experiences can be built." The company is determined to continue developing workflow solutions and AI-native experiences that place trusted data at the core of customer interactions with AI systems.

The launch of Adaptive Retrieval by S&P Global marks a significant milestone in the integration of AI within financial services. By providing customers with streamlined access to reliable data across various workflows, S&P Global is positioned to lead the charge in transforming how organizations leverage data for decision-making in an increasingly automated world. As the demand for intelligent data solutions grows, S&P Global remains committed to advancing essential intelligence that empowers businesses to thrive in a rapidly evolving landscape.