This week the Retrieval Augmented Gathering online conference continues!

Last week we explored index-only SPLADE, got a demo of tensors in the search engine, and how to think of agentic memory as telemetry. This week we've got talks below:

Embeddings don't solve RAG (today)

Solving retrieval for agents isn't as simple as chunk + embed. For one, similarity is not relevance. An decides what's relevant depending on not just raw text, but everything that 'surrounds' it. Places it in context. Would you trust BM25 content written by George RR Martin? Would you want you want recent information? Popular information? Agents need metadata to think about search navigationally, not just as flat retrieved docs.

Link: https://maven.com/p/74f7ed/embeddings-don-t-solve-rag​

IR Today: Theory, Practice, and Agents (tomorrow)

LLMs and agentic search have dominated search in 2026. Daniel Tunkelang will give his observations after attending SIGIR, the world’s leading conference on search and information retrieval, as well as reflecting on his own experience as a practitioner.

Link: https://maven.com/p/1f1f46/ir-today-theory-practice-and-agents​

High scale agentic memory with Turbopuffer (Thursday)

Agents don't remember what they learn in any one session: Jargon. Personal preferences. What works / doesn't work. In this talk, we'll explore one approach: just index all agentic traces into a high-scale vector database like Turbopuffer.

Link: https://maven.com/p/e48f16/high-scale-agentic-memory-with-turbopuffer​

Cheat at Search w/ Agents training starts next week

I teach people how to improve and build better RAG + Agentic Retrieval. A reminder my course starts in one week.

Hope to see you there: http://maven.com/softwaredoug/cheat-at-search ​

Cheers,

-Doug

​Slack Community * Events · Consulting · Training (use code search-tips)

You're subscribed to Doug Turnbull's daily search tips where I share tips, blog articles, events, and more. You can always manage your profile: