Rethink search to put tireless agents at work for human users

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

YouTube video by Doug Turnbull

Rethink search to put tireless agents at work for human users

Rethink search to put tireless agents at work for human users

Live courses with real-world experts in AI, Product, Leadership, Design, Data & engineering, Marketing & sales, and Business & finance.

Posted by softwaredoug - 1 vote and 0 comments

A proposed third phase of Dairy Market brought the 10th and Page Neighborhood Association and Stony Point Development Group face-to-face Wednesday night.

New Private Housing Structures Authorized by Building Permits for Charlottesville City, VA

RAG and Agentic search requires vector search. And increasingly multi-vector retrieval. Vespa's tensor feature implements vector search. "How are tensors better than vectors?" is a common follow-up q...

Kicking the tires of jev for a very basic query understanding task

Live courses with real-world experts in AI, Product, Leadership, Design, Data & engineering, Marketing & sales, and Business & finance.

Rethink search to put tireless agents at work for human users

YouTube video by Doug Turnbull

Rethink search to put tireless agents at work for human users

What you should be thinking of as you consider search + retrieval roles

Live courses with real-world experts in AI, Product, Leadership, Design, Data & engineering, Marketing & sales, and Business & finance.

Rethink search to put tireless agents at work for human users

Live courses with real-world experts in AI, Product, Leadership, Design, Data & engineering, Marketing & sales, and Business & finance.

You've been fed a false narrative. That RAG means embeddings. Ask a retrieval engineer they'll only be one small piece of a good RAG solution. By questioning embeddings as a search solution, we'll tak...

It's scary out there. Skills we thought would be timeless are being brought into question. We're all being asked to relearn our career as agentic coding continues to eat software development. Search r...

A technique for deterministic labeling from stochastic models, with benchmarked Golang implementation.

Build and reason about enterprise agents grounded in your team's knowledge base

Build and reason about enterprise agents grounded in your team's knowledge base

My biased search expert perspective on where new AI teams run into expensive and unfortunate mistakes

A useful pattern for LLM classification at scale is to let it hallucinate plausible, fake entities. Then resolve to real ones.

Make embedding retrieval an asset, not a headache

A useful pattern for LLM classification at scale is to let it hallucinate plausible, fake entities. Then resolve to real ones.

Choosing a vector database is an expensive, sticky decision often made using feature lists and generic benchmarks. Teams commit, load their real corpus, then discover costs far above budget. By then, ...

A week of wector wevents - vector retrieval, hybrid search, combining the dense and lexical.