{"slug": "launch-hn-agnost-ai-yc-s26-extract-user-feedback-from-agent-conversations", "title": "Launch HN: Agnost AI (YC S26) – Extract user feedback from agent conversations", "summary": "Agnost AI, backed by Y Combinator, launched a tool that extracts user feedback from AI agent conversations to identify failures and suggest improvements. The platform works with any LLM or framework, offering features like intent extraction, failure detection, and automatic agent improvements.", "body_md": "Backed by Y Combinator\n\nwhy agnost\n\n## Your evals pass. Production still fails.\n\nAgnost finds the missed failures in real conversations and turns them into fixes your team can review.\n\n“In collaboration with Agnost AI, we have integrated comprehensive observability features into MCP Toolbox for Databases.”\n\n“Agnost AI is very useful in tracking analytics and error rates.”\n\n“Our Voice BDRs got meaningfully better at booking meetings once Agnost AI surfaced the patterns behind the conversations that actually converted.”\n\n“Agnost AI showed me users were asking for features we don't even have. I had no idea. All that feedback was just sitting inside conversations we already had.”\n\n“Agnost AI is how we make our agents better. We see what to improve, ship it, and move faster. Simple as that.”\n\n“Agnost AI spotted bugs buried in our agent's conversations and opened PRs to fix them overnight.”\n\nINTENTS·SIGNALS·IMPROVEMENT\n\n## From silent production failures to the fix that ships.\n\nWorks with any LLM, any framework. 2-min setup. OpenTelemetry native.\n\n### See the failures your evals missed.\n\nThe moment you connect, Agnost AI reads real production conversations and generates the failure categories that matter to your product: broken workflows, repeated retries, setup friction, churn risk, and more.\n\n## Start free.\n\nScale when you're ready.\n\nThe earlier you start ingesting conversations, the smarter your agent gets, so connect today.\n\n- Intent & sentiment signal extraction\n- Automatic agent improvements\n- Failure detection & resolution\n- Natural language data queries\n- Up to 1,000 messages / mo\n- 7-day data retention\n\nBest for teams shipping agents that need to get better fast.\n\n[Start free](https://app.agnost.ai)\n\n- Everything in Starter\n- Up to 100,000 messages / mo\n- 90-day data retention\n- Priority support\n- Founders Slack channel\n\nBest for growing teams scaling agent volume without a sales call.\n\n[Start now](https://app.agnost.ai)\n\n- Custom data retention\n- Audit logs\n- Custom SLAs & SLOs\n- Custom improvement workflows\n- Priority feature requests\n- Founders Slack channel\n- Unlimited time with the founders\n\nBest for organizations running agents at scale.\n\n[Let's chat](https://cal.com/shubhamintech/agnost-enterprise-call)\n\nfrequently Asked Questions", "url": "https://wpnews.pro/news/launch-hn-agnost-ai-yc-s26-extract-user-feedback-from-agent-conversations", "canonical_source": "https://agnost.ai", "published_at": "2026-07-14 16:06:18+00:00", "updated_at": "2026-07-14 16:31:30.163250+00:00", "lang": "en", "topics": ["ai-tools", "ai-products", "ai-startups", "ai-agents"], "entities": ["Agnost AI", "Y Combinator"], "alternates": {"html": "https://wpnews.pro/news/launch-hn-agnost-ai-yc-s26-extract-user-feedback-from-agent-conversations", "markdown": "https://wpnews.pro/news/launch-hn-agnost-ai-yc-s26-extract-user-feedback-from-agent-conversations.md", "text": "https://wpnews.pro/news/launch-hn-agnost-ai-yc-s26-extract-user-feedback-from-agent-conversations.txt", "jsonld": "https://wpnews.pro/news/launch-hn-agnost-ai-yc-s26-extract-user-feedback-from-agent-conversations.jsonld"}}