■ NewsInsight from the intersection of AI and business
Product updates, research, customer stories, and perspectives from the team building AI at S&P Global.
NewsArchive
Kensho MCP Apps: Visualize, explore, and interact with S&P Global data inside AI applications
Financial professionals increasingly work inside AI applications like Claude and ChatGPT, but most information they get back is locked in static text. Kensho MCP Apps change that. We've built a suite of applications embedded directly inside AI chat interfaces that turn S&P Global’s data into interactive charts, tables, visualizations, and more, all without ever leaving the conversation. Customers can explore, filter, and ask follow-up questions about the charts and tables in real time, making research faster and more intuitive. Kensho MCP Apps are now available in beta for select customers.
Building on moving ground: Life as an MLOps engineer at Kensho
Over the past two years as an MLOps engineer at Kensho, I’ve come to appreciate both the challenges and the immense value of operating in an environment where implementation patterns, tools, and the surrounding ecosystem are constantly changing.
How Kensho built a multi-agent framework with LangGraph to solve trusted financial data retrieval
Discover how Kensho, S&P Global’s AI innovation engine, leveraged LangGraph to create its Grounding framework–a unified agentic access layer solving fragmented financial data retrieval at enterprise scale.
Inside Kensho’s LLM-ready API: How engineers enable secure natural language access to S&P Global data
Three engineers share how Kensho — S&P Global's AI innovation engine — built and scaled the Kensho LLM-ready API to deliver financial intelligence wherever customers work.
Kensho LLM-Ready API adds Private Company Financials, S&P Capital IQ Estimates datasets, and enhanced auditability for public company financials
Kensho LLM-Ready API now features access to S&P Global Private Company Financials and S&P Capital IQ Estimates data, along with in-line source document links for existing S&P Global public financials data. These enhancements unlock new possibilities for AI-driven financial analysis workflows to enable deeper insights, transparency, and confidence in data-driven decision-making.
Kensho LLM-ready API expands MCP server access, dataset support, integrations, and more
Announcing remote MCP server support for the Kensho LLM-ready API, which makes it even easier to access trusted S&P Global datasets as a Connector in Claude, or through any MCP-supported GenAI tool. We’ve also rolled out new capabilities and support for a wealth of financial datasets to enable more customer use cases and workflows, from earnings to private markets and beyond.
Designing trustworthy AI: Principles for effective human-AI teaming in finance
A human-AI collaboration approach can ensure trust, transparency, and control when designing generative AI applications. We outline key design principles to help organizations safely deploy agentic AI in financial environments.
The Future of S&P AI Benchmarks
Benchmarks have a natural lifecycle. As generative AI evolves and large language models (LLMs) improve ever more rapidly, model performance has progressed to the point where our benchmarks have served their purpose. As our research enters a new phase, we are sunsetting S&P AI Benchmarks by Kensho and will no longer be updating our public leaderboards. We want to explain why we’re making this change, and what it means for our customers and the industry.
S&P Global and Anthropic announce collaboration to bring trusted financial data into Claude
We developed a cutting-edge Model Context Protocol (MCP) server enabling seamless access to S&P Global’s trusted financial and market data through Claude by Anthropic. This integration connects the Kensho LLM-ready API and its wealth of S&P Global datasets–including S&P Capital IQ Financials, earnings call transcripts, and more–to Anthopic’s new Claude for Financial Services Solution.
Announcing Figure Extraction: Unlocking generative AI insights from data visualizations in PDF documents
We’re excited to launch a game-changing new Kensho Extract feature: Figure Extraction is a patent-pending technology capable of extracting hundreds of data points from PDF visualizations with high numerical accuracy.
S&P Global launches Kensho LLM-ready API (beta), making its structured data accessible for generative AI
New solution enables customers to seamlessly integrate complex, high-priority S&P Global datasets into Generative AI models.
We’re expanding S&P AI Benchmarks to cover long-document QA
New benchmark assesses how well AI systems analyze complex financial documents hundreds of pages long.
Unlocking precision and speed: Discover the latest enhancements to Kensho Scribe
We are excited to introduce the latest update to Kensho Scribe AI, our speech-to-text transcription tool. From meeting note documentation to earnings call transcription, our enhanced model offers cutting-edge technology to streamline your workflow and deliver precise results. This new model delivers a 30% reduction in errors compared to our previous model while significantly increasing output quality. These latest advancements can transform your transcription experience and drive greater efficiency in your operations.
Enhanced document extraction for generative AI use cases
Introducing Kenverters, a set of open source Python developer tools for fast and easy use of Kensho Extract in pipelines for Retrieval Augmented Generation (RAG), Large Language Models (LLMs), table extraction, and more!
4 key takeaways from our workshop at HCII2024
During our recent workshop at the Human-Computer Interaction International Conference (HCII2024), we delved into the intersection of the evolving landscape of AI models, human-centric design, and the growing field of financial AI. Here are four key takeaways from our workshop, offering insights into how these areas shape designing AI applications.
An Introduction to mitigating toxicity in LLMs - Pt. 2
In our last post, we introduced toxicity as a challenge when building LLMs and various methodologies to mitigate it. In this post, we’re going to focus on utilizing one of those methodologies — auxiliary tools — and assessing some tools that are available to the public.
How Kensho Collab Week strengthens our culture and accelerates S&P Global’s AI strategy
Last month, Kenshins came together at Kensho’s Cambridge, MA headquarters for Collab Week — a week of face-to-face connection and collaboration. While we have embraced a hybrid work culture across our offices, there’s high value in meeting in person to move important projects forward and help us all work better together.
■ Get startedTalk to our team about what’s possible
At Kensho, you’ll work at the intersection of trusted data, advanced AI, and real-world decision-making. We hire talented people and give them autonomy and support to develop cutting-edge solutions that solve complex business problems.