Many developers are eager to seek tricks to improve the RAG answer quality, but fail to realize that this is a system optimization problem. Changing one component does not guarantee good overall performance unless there is a scientific way to test the end-to-end quality.

Yup! Claude 3.7-sonnet’s personality is to remove your tests and then claim victory! 😅 “Eval Agents” by Dhruv Singh

Dhruv Singh (Co-Founder, CTO HoneyHive) gives agent evals the time they deserve with his talk “Eval Agents: How to Solve Error Cascades in Agents.” Why do these agentic systems spiral into failure, and how do we catch it early? Quietly one of the most important talks of the

🧭 𝐀𝐝𝐚𝐩𝐭𝐚𝐛𝐥𝐞 𝐑𝐞𝐜𝐨𝐦𝐦𝐞𝐧𝐝𝐚𝐭𝐢𝐨𝐧𝐬 𝐨𝐮𝐭𝐬𝐢𝐝𝐞 𝐨𝐟 𝐭𝐡𝐞 𝐒𝐢𝐦𝐢𝐥𝐚𝐫𝐢𝐭𝐲 𝐁𝐮𝐛𝐛𝐥𝐞 𝐰𝐢𝐭𝐡 Qdrant 𝐚𝐧𝐝 HoneyHive. Discovery is exciting: new ideas, books, songs, food! Yet it’s hard to find a perfect framework for it. Recommendation algorithms

🚀Observability and AI are converging, reshaping IT operations. This fusion enhances system insights and AI performance monitoring. Explore how tools like Honeyhive and Arize's Phoenix are leading this transformation! HoneyHive arize-phoenix 🔗 Read more⬇️📖

Today we're shipping some major quality-of-life improvements to traces 🎁 🔍 Session Summaries: Unified view of metrics, evals, and feedback across all spans in an agent session. No more jumping between individual spans. ⏱️ Timeline View: Flamegraph visualization to identify

Introducing Alerts🔔 Alerts in HoneyHive give you real-time monitoring over everything that matters in your agent: ✅ Metric drift - Detect quality degradation over time ✅ Cost spikes - Stay within budget thresholds with usage alerts ✅ Guardrail violations - Monitor safety

Hear from the software leaders driving AI forward on why they’re excited for ScaleUp:AI (just two weeks away!) — and stayed tuned to hear what’s next for the future of the industry. Featuring: • Kiteworks' CEO Jonathan Yaron • Lightrun's Cofounder and CEO Ilan Peleg •