Yesterday I received my author copies of the "Hands on RAG for production" - it was very exciting to hold in my hand the actual physical copy, after so many months of work. amazon.com/Hands-RAG-Product… @OReillyMedia

Great week in Alberta — our CEO Kyle Nesbit joined Data Foundations workshops in Edmonton & Calgary. Going from "we have data" to "we trust our data" is the whole game. Most stacks never make the jump — nobody builds end-to-end. Thanks to DAMA Edmonton, DAMA Calgary, YYC Data Society & Data For Good YEG for hosting, and to everyone who brought real questions and energy 🙌 #DAMA #SemanticLayer #ContextEngineering

This is starting tomorrow morning…

This Friday, June 12, we kick off the @band_hq hackathon - now with 3,200 participants 🚀 There’s still time to join and build something cool with agent-to-agent communication. If you’re interested in multi-agent workflows or the emerging Internet of Agents, come and build with us. lablab.ai/ai-hackathons/band… #AI #Agents #Hackathon

The agent framework trap: Every framework makes the first agent easy. The second agent is easy too, as long as it uses the same framework. Then reality shows up: LangGraph needs to coordinate with CrewAI. Claude SDK needs to hand off to OpenAI Agents SDK. Vendor agents enter the picture. Suddenly you’re maintaining custom glue code for every pairwise integration. The future of agent systems won’t be built on one framework. It will need a framework-agnostic layer for state, routing, and lifecycle. Read the full post: band.ai/blog/agent-framework…

Had a great time yesterday at @arizeai observer 2026, presenting about Agent-to-agent communications using @band_hq, and what it takes to get true end-to-end observability over cross-framework agentic flows in production. More here: band.ai/blog/when-trace-stop… Thanks @aparnadhinak @dat_attacked @seldo and the entire Arize team.

More than 2,200 builders have already signed up. And we're still 1 week away from kickoff! The Band of Agents Hackathon with @lablabai is officially live - a full week of building enterprise multi-agent systems where agents actually communicate, coordinate, and complete real work together - as a team. $10,000 in prizes. Fully online, built from anywhere. The challenge is simple - at least 3 agents collaborating through BAND across planning, execution, review, and decision-making. The rest is up to you. June 12-19. Registration's open. More details here: lablab.ai/ai-hackathons/band…

Excited to be speaking at @arizeai Observe this Thursday about @band_hq and observability with agent to agnet communciations. If you're there, please come by to say hi!

After many months of writing, editing, and trying to turn hard-won RAG lessons into something useful, our book "Hands-On RAG for Production" is now live on O’Reilly 🎉 learning.oreilly.com/library… The book is for engineers and AI teams building real production RAG systems. The book covers architecture, ingestion, embeddings and vector search, reranking, evaluation, hallucinations, latency/cost tradeoffs, enterprise deployment, agentic RAG, multimodal RAG, as well as GraphRAG. It's available on Amazon for pre-order, and I'm told would be shippable within a few weeks. A big thanks to everyone who helped bring this to life: my co-author @forrestbao, the wonderful team at @OReillyMedia, as well as @realSharonZhou, @jim_dowling, @tallatmshafaat, @awadallah, @EvaNahari, @MaxWBuckley, @bobvanluijt, @jerryjliu0, @steveonjava and so many others.

Excited to be speaking at @arizeai observe on June 4th about why traces alone are not enough for true observability in multi-agent systems, and how you can solve it with @band_hq.

We're proud to see our Co-Founder and CEO, @g00manoid , featured in VentureBeat's latest article - read more on how he sees the next opportunities for multi-agent systems 🤖 venturebeat.com/orchestratio…

Day 1 of @AICouncilConf afternoon - @petesoder on stage with a wonderful performance about the future of AI - thank you Pete, that was awesome!

Announcing Codeband: an open-source way to connect Claude Code Codex through @band_hq. github.com/thenvoi/codeband Using them together feels like ensemble learning for coding agents: one builds, another reviews, and cross-model disagreement becomes a feature, not a bug. More on why five Claudes are not a good team: band.ai/blog/five-claudes-ar…

Using Claude Code Codex on the same task feels like ensemble learning from ML, just for coding agents. Different agents. Different failure modes. The magic is not picking the “best” agent, but combining imperfect ones into a better result.