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. As S&P Global’s engine for AI innovation and transformation, Kensho ’s goal is to ensure that as AI transforms industries, its outputs remain grounded in trusted data–however and wherever customers choose to use it. We hope these best practices will help guide other organizations when developing complex multi-agent architectures: 1.
- Agent or tool
- LangChain
- Topic
- Sales & Marketing
- Reported on
- Blog (LangChain)
- Added
- 2026-11-11
Why it matters
Sales and marketing run on research, lists and follow-ups. Agents are starting to take on that groundwork, freeing people for the conversations that actually close deals. It is one of 613 sightings filed under Sales & Marketing on Agent Sightings (number 379 by interest), and one of 25 involving LangChain.
How you could try it
Here is a reusable prompt, written by us in our own words, that captures the task. Paste it into LangChain or any similar agent and adjust the details to your situation.
I want an agent to do the research and drafting for this sales or marketing workflow, and stop for my approval before anything is sent. The tool in the source case was LangChain.
Tip: Start small: run it once on a low-stakes example, read what the agent did, and only then let it run on real work.
Source
Read the original first-hand account on Blog (LangChain): https://langchain.com/blog/customers-kensho. Our summary is a paraphrase; details are in the source.
Built an AI agent? Feature your agent on Agent Sightings, free submission or a featured spot.
Browse more like this
Related sightings
- Improving Memory Retrieval: How New Computer achieved 50% higher recall with LangSmith
- How Workday Built an Enterprise-Scale AI Agent Platform with LangGraph and LangSmith
- How Tradestack launched their MVP in 6 weeks using LangGraph Cloud
- “Get your hands dirty:” Safari365’s CEO shares why execs should roll up their sleeves with Agentforce.
- How Minimal built a multi-agent customer support system with LangGraph & LangSmith
- How Klarna's AI assistant redefined customer support at scale for 85 million active users