Agnost AI: Analyzing Agent Conversation Feedback

laalshaitaan · hn · 2026-07-15

Agnost AI has launched on HN, positioning itself as "product analytics for conversations" tailored for chat and voice agent teams.

It ingests production conversations to automatically detect behavioral failures: users repeating themselves, cursing at the agent, correcting it, asking for missing features, or leaving despite getting an answer. The team integrates messages via SDK or OTel, combining metadata like account, plan, source, and organization to cluster conversations into product intents. It identifies feature requests and bugs by default, while other categories evolve dynamically based on customer data.

The founders emphasize that this product differs from observability or evals: the former monitors technical events, and the latter validates known cases. Instead, they focus on "what users actually want, where they get stuck, and what new evals should be added."

Original post →

More from coding & agent

coding & agent channel →