1/ We’re thrilled to announce we've raised $7.4M in total funding led by @InsightPartners along with @ZeroPrimeVC, @AIXVenturesHQ, @468Capital, and @FirestreakVC to bring evals and observability to AI agents. HoneyHive Cloud is also generally available starting today.

What's new:.✅ Two-tier permissions (Org + Project levels).✅ Project-specific API keys & user controls.✅ Granular security for sensitive operations.✅ Seamless migration for existing users. Learn more:

Introducing Role-Based Access Control (RBAC) in @HoneyHiveAI!. Built in partnership with our largest financial services and insurance customers, RBAC brings enterprise-grade security and access controls to your critical observability workflows.

The most successful AI teams understand this shift:. ❌ Don't optimize for general capabilities on academic tests .✅ Build evals that predict your specific failure modes. What actually matters: Decompose your system architecture, understand LLM-judge biases, and continuously.

Chasing benchmark leaderboards is the easiest way to build an AI product that fails in the real world. Most teams waste 90% of their eval effort on academic benchmarks instead of finding exactly where their system breaks with real users.

Full announcement:

We're excited to announce that HoneyHive has officially achieved SOC 2 Type II, GDPR, and HIPAA compliance!. Every LLM interaction today—from user prompts to contextual retrieval or tool-use data—contains potential PII and PHI, which is why we've built our platform with

RT @startreedata: 🚀Observability and AI are converging, reshaping IT operations. This fusion enhances system insights and AI performance….

RT @qdrant_engine: 🧭 𝐀𝐝𝐚𝐩𝐭𝐚𝐛𝐥𝐞 𝐑𝐞𝐜𝐨𝐦𝐦𝐞𝐧𝐝𝐚𝐭𝐢𝐨𝐧𝐬 𝐨𝐮𝐭𝐬𝐢𝐝𝐞 𝐨𝐟 𝐭𝐡𝐞 𝐒𝐢𝐦𝐢𝐥𝐚𝐫𝐢𝐭𝐲 𝐁𝐮𝐛𝐛𝐥𝐞 𝐰𝐢𝐭𝐡 Qdrant 𝐚𝐧𝐝 HoneyHive. Discovery is exciting: new idea….

🔑 Why this matters:. - It goes beyond simple similarity matching by creating dynamic context pairs from user feedback.- The system avoids "similarity bubbles" that constrain discovery.- It adapts to user feedback in real time without requiring a well-defined request. We've.

Traditional vector search systems often struggle with nuanced user preferences that are difficult to articulate. Our latest collaboration with @qdrant_engine showcases an iterative optimization technique that dynamically adapts search results based on user preferences.

RT @etiennedi: Yup! Claude 3.7-sonnet’s personality is to remove your tests and then claim victory! 😅 . “Eval Agents” by @ds3638 https://t….

RT @DataCouncilAI: @ds3638 (Co-Founder, CTO @honeyhiveai) gives agent evals the time they deserve with his talk “Eval Agents: How to Solve….

RT @zilliz_universe: Many developers are eager to seek tricks to improve the RAG answer quality, but fail to realize that this is a system….

Learn more:

RAG doesn’t work? Wrong. Most developers just can’t see why it doesn’t. Our latest integration with @zilliz_universe / @milvusio brings tracing, evals, and optimization tools to the vector database you know and love, helping you systematically improve your retrieval quality.

RT @qdrant_engine: 🔎 See inside your RAG pipeline with Qdrant + @honeyhiveai . You can now trace every step of retrieval and generation: em….

Check out our full integration guide:

With @qdrant_engine's blazing-fast search and HoneyHive’s LLM evals platform, you can:-. 1️⃣ Evaluate your Qdrant retrieval pipeline with metrics like context relevance and context precision/recall .2️⃣ Identify improvements and regressions as you optimize search parameters (chunk

By popular demand, we’re excited to introduce an integration with @qdrant_engine!. Retrieval powers most AI apps today, but it's so hard to get right. From simple KNN to agentic RAG, how do you know what search strategy works best for your use case?. Enter HoneyHive + Qdrant 🤝

RT @lancedb: Hard to debug & optimize your RAG apps in production? 🤔 .LanceDB <> @honeyhiveai integration gives you the visibility you nee….