S&P Global launches dual data retrieval for AI agents

S&P Global announced the launch of Adaptive Retrieval on the strength of a recognized industry need: as AI agents and large language models become central to enterprise workflows, these systems must reliably access trusted, cited data without requiring months of data preparation and engineering. The new Adaptive Retrieval service allows customer AI agents and LLMs to access and assemble licensed S&P Global data using natural language queries and automatically handle requests that involve multiple datasets.

Adaptive Retrieval is purpose-built for complex, multi-step tasks, including in-depth research and report generation. It lets AI agents pull data from many different sources at once—a capability well-suited to autonomous, multi-agent systems where tasks span multiple data domains. Alongside Adaptive Retrieval, S&P Global continues to offer Deterministic Retrieval, which was built on the Kensho LLM-ready API and has been available to customers since 2025. Deterministic Retrieval gives AI systems API-driven access to S&P Global data through direct, structured queries and is ideal for focused tasks such as researching a specific company or analyzing earnings call transcripts. Both methods are now available through a single platform called the S&P Global AI Data Portal, and customers can use one method or both depending on how their systems are set up and what they need to accomplish.

The underlying motivation, according to Sally Moore, Chief Client Officer and Co-Head of Market Intelligence, is to ensure that S&P Global's trusted data is accessible across the full range of workflows. "The use of AI in financial services is rapidly accelerating and evolving, from tightly controlled workflows to fully autonomous, multi-agent systems," she said. "With Deterministic and Adaptive Retrieval now available together, we're ensuring that S&P Global's trusted data is accessible across that full range of workflows, so customers can access data the way they need it today and adapt as their architectures evolve."

Historically, embedding high-quality financial data into AI systems has demanded significant engineering work—finding and validating sources and building the logic to retrieve them accurately, a process requiring deep domain expertise. With both Adaptive and Deterministic Retrieval available through the S&P Global AI Data Portal, S&P Global aims to eliminate that complexity. Its data is already cited, structured, and ready for AI systems to use, allowing customers to focus on building products and generating insights rather than preparing and managing data. Bhavesh Dayalji, Head of Kensho Data & Intelligence, framed this as a foundation: "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." He noted that S&P Global data now flows directly into the tools and platforms where customers work—including Capital IQ Pro, financial skills and plugins, and Model Context Protocol (MCP) apps—allowing customers to visualize, explore, and interact with S&P Global data inside AI applications. This launch is part of a broader evolution of S&P Global's Market Intelligence operating model, which brings together data, AI, software, and workflow capabilities and reflects the role of the newly formed Kensho Data Platforms vertical in delivering world-class client interfaces and AI-native user experiences.

S&P Global's launch reflects a fundamental shift in how enterprises deploy AI systems. The company recognizes that as organizations move beyond tightly controlled AI pipelines to autonomous, multi-agent systems, the data infrastructure must evolve alongside. By offering two complementary retrieval methods—one for flexibility and complexity, one for precision and control—S&P Global is positioning itself to serve the full spectrum of AI adoption paths that customers may take.

The timing aligns with the company's broader evolution. The announcement follows S&P Global's recently announced reorganization of its Market Intelligence operating model, which integrates data, AI, software, and workflow capabilities. Kensho Data Platforms, the newly formed vertical within Market Intelligence, is central to this vision: it is developing AI-native interfaces like Capital IQ Pro and enabling S&P Global data to flow into tools, plugins, and Model Context Protocol (MCP) apps where customers already work. In this context, Adaptive and Deterministic Retrieval are not isolated data services but foundational layers upon which higher-value AI-native experiences can be built.

The practical appeal is significant for enterprise customers. Historically, embedding proprietary financial and market data into AI systems demanded deep domain expertise and custom engineering—finding sources, validating them, and building retrieval logic. By pre-structuring its data and offering both natural-language and API-driven access methods, S&P Global reduces friction for customers building their own AI products while maintaining the auditability and verifiability that regulated financial services demand.

No comments yet. Be the first to share your thoughts!