Source record

Published by LangChain Blog (T1.5 source). The original is at https://www.langchain.com/blog/how-pendo-used-langsmith-to-trace-novus-from-user-behavior-to-code-fixes.

Pipeline notes

The summary and note below are generated by the signal pipeline — they are Beyond Desk’s reading, not quotations from the source.

Pendo built Novus, an AI agent that detects usability issues in live applications and auto-generates code fixes from behavioral data and session replays. The team used LangSmith to trace, evaluate, and monitor the agent, reporting 90%+ accuracy on PM-reviewed evals and a production ship in days.

A real production agent case study, but mostly a vendor guest post; the PM-developer feedback-loop framing is the one durable insight worth extracting.

Cited by

No citations on record.