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.

Langchain is a publication focusing on programming languages, language design, and compiler development. Readers can explore articles covering topics such as language features, syntax design, and compiler optimization techniques. Additionally, they can learn about programming language theory, language implementation challenges, and practical applications of language design principles.

LangChain

Kensho, S&P Global's AI innovation arm, built a multi-agent framework called Grounding using LangGraph to unify fragmented financial data retrieval across S&P Global's diverse datasets. The system uses a central router that directs natural language queries to specialized Data Retrieval Agents (DRAs) owned by different data teams (equity research, fixed income, macroeconomics, etc.). A custom DRA protocol standardizes data formats across all agents, enabling consistent, citation-backed responses. Key lessons include the importance of observability via LangGraph's tracing, multi-stage evaluation covering routing accuracy and data quality, and continuous protocol optimization for both LLM and programmatic consumption.

How Kensho built a multi-agent framework with LangGraph to solve trusted financial data retrieval

The Challenge: Fragmented Financial Data Retrieval

Designing a Multi-Agent Framework with LangGraph

Establishing a Custom Data Retrieval Protocol

Key Learnings for an Evolving Agentic Ecosystem