How Morningstar Stopped Flying Blind on Production Agents with LangSmith
Morningstar deployed LangSmith to gain observability into production AI agents after flying blind
“Without LangSmith, we didn't have a common language for observability and tracing. And so debugging becomes anecdotal.”
Morningstar's AI accelerator team adopted LangSmith to replace ad-hoc Splunk queries for tracing production agents embedded in Morningstar Direct and a live MCP server. The move addressed a visibility gap where teams had no shared observability language, making debugging anecdotal. While a real-world enterprise agentic deployment story, this is primarily a vendor case study with limited novel signal.