Building a retrieval system is one thing. Knowing whether it’s actually good is another. This practical guide walks through how to evaluate information retrieval systems using a Qdrant-powered retrieval pipeline and Evret. It covers: → Building a retrieval benchmark → Measuring retrieval quality → Evaluating relevance and ranking performance → Moving beyond “it seems to work” testing As RAG and retrieval systems become more critical in production AI applications, evaluation is becoming just as important as retrieval itself. Read here: medium.com/data-science-coll…

to name a few... @rimelabs: jobs.ashbyhq.com/rime, SF/NY @qdrant_engine: jobs.ashbyhq.com/qdrant.tech, global @AirOpsHQ: jobs.ashbyhq.com/airops, global @GovSignals: jobs.ashbyhq.com/GovSignals, NY/DC @vizcom: vizcom.com/careers#open-role…, SF/remote

Building AI agents in Rust? This post is for you 🦀 Over the last month, I’ve been building 𝗺𝗶𝗰𝗿𝗼𝗮𝗴𝗲𝗻𝘁𝘀, a Rust-native, modular framework for creating AI agents with minimal overhead. Some highlights: ⚡ Multi-provider LLM support 🔄 Event-driven architecture with JSON-RPC compatibility 💾 Session persistence across multiple storage backends 🛠️ Skills and custom tool definitions 🖥️ Batteries-included TUI featuring out-of-the-box tools to: • Read text files, PDFs, Office documents, and images with @llama_index LiteParse • Edit and write files • Execute Bash commands • Perform hybrid search across your workspace powered by @qdrant_engine Edge Run local and cloud models through a unified experience. Interested in learning more? 🔗 microag.clelia.dev ⭐ GitHub: github.com/AstraBert/microag… PS: A technical deep dive is coming soon... 📝

That's a badass photo indeed, wow!

love it!

Had a lot of fun talking about retrieval in the agent of agents at the Vector Space meetup in Berlin on Thursday!🚀 Together with @qdrant_engine, @deepset_ai, @cognee_ and @n8n_io, we discussed a broad range of topics, from evals to architecture decisions to hot takes... But the panel was just the beginning: the room was packed with so many brilliant people and I had many genuinely interesting conversations about how to run agents and retrieval systems in production🤖 Huge thanks to the Qdrant team for organizing this!🙌 PS: if you're doing events around agents, retrieval and how to harness/evaluate them, esp in Germany🇩🇪 and EU🇪🇺, feel free to reach out, always happy to give my contribution👩‍💻

Can we watch it on YouTube or elsewhere? Looks amazing

@mem0ai @qdrant_engine @zep_ai

One insight from an AI Leaders dinner this week: 97% accuracy may be good enough for @DoorDash. For pharma and drug discovery, it can be catastrophic. As AI moves into higher-stakes domains, the focus shifts from models to data quality, retrieval, and infrastructure. That's why technologies like @qdrant_engine are becoming increasingly critical.

This aligns with what AI leaders around the table shared: better models help, but better data, retrieval, and observability matter more.

What a search week in Berlin! 🇩🇪 On Tuesday, we hosted "Retrieve. Remember. Reason" at the @deepset_ai offices, organized with @OpenSearchProj and @cognee_, featuring Women of Search (@atitaarora 🙏), where I got to demo what's possible with a knowledge base, memory, and @Haystack_AI's orchestration capabilities. More than half the room was women, which is rare and wonderful at tech meetups! 🫶 Then yesterday, I joined the Vector Space Meetup panel at @aicampusberlin, alongside @qdrant_engine, @cognee_, @llama_index, and @n8n_io, to talk about retrieval strategies, evaluation, orchestration, and what actually goes into production. Great panel and amazing networking session! Kudos to @krotenWanderung and the team It was a great week where I learned so much. Already looking forward to the next thing!

Amazing talk. Definitely in my top 3 for Vector Space day

Absolutely awesome @DynamicWebPaige !!

evaluation is the part everyone skips until prod breaks and theyre scrambling the precision vs recall tradeoff talk usually makes people glaze over too

Spent Wednesday evening at a very good event in SF: "Fixing Broken Retrieval," put on by the @mlopscommunity and @qdrant_engine. I did my bit on closing the loop on agent failures, but honestly the two talks after mine are the ones I keep thinking about. Dylan from Qdrant walked through building self-correcting retrieval loops, and it was that rare talk that is genuinely technical and still easy to follow. Amanda, founder of azenticbot.ai, took the harder question nobody likes: what an agent should do when retrieval fails and it is not sure. Governing decisions under uncertainty is the unglamorous corner of this whole field, and she made it the most interesting thing in the room. The crowd was the other highlight. ✨ Big thanks to Arthur, MLOps and Qdrant crew for having me, and to Vrinda for roping me in. Let's do it again.

the evaluation part is always the hardest part, nice work.

Last night, @Unusual_VC & @qdrant_engine hosted The Retrieval Reckoning, an intimate dinner with 13 engineering leaders building AI systems at scale. A few themes emerged: → Data quality remains a bigger challenge than model quality. → Retrieval has evolved from a backend feature to mission-critical infrastructure. → Observability, governance, and trust are becoming the defining challenges of production AI. → The future of agentic systems will be shaped as much by memory and retrieval as by the models themselves. Excited for the next one!

I went to space today. 🚀 Well, Vector Space Day. The event theme was astronauts, NASA helmets, and "Don't Get Lost in Vector Space." But beneath the space jokes, the discussions were a good reflection of where these companies are going with AI. The focus was on memory, retrieval, context, evaluation, and what it takes to build AI systems people can actually rely on. There were also discussions on how much to build for the AI agents vs. Humans themselves because the whole point is these products started with human needs and are getting too blurred with Agents hopping into these systems. It was particularly interesting to hear the panel discussion from @SlackHQ & @qdrant_engine and presentation by @HubSpot sharing their perspective. And yes, I absolutely put on the astronaut helmet 🚀 #Qdrant #VectorSearch #AIEngineering #AIAgents #VectorSpaceDay