I share search tips, blog articles, and free events I'm hosting about the search+retreval industry, vector databases, information retrieval and more.
A fun week of search before Cheat at Search starts
|
It's the final week before my Cheat at Search with Agents course. But we've got a fun tailgaite party before the big event ๐. Agent harnesses are dead - long live harnessesToday, 7PM ET - https://maven.com/p/6dc9ef/building-effective-agent-harnessesโ Search backend design means agent design. Hugo Bowne Anderson lives by a KISS ethos - Keep it Simple Smartypants. He talks real-life production LLM + harness design. You don't need to chase the latest OpenClaw -> Hermes -> Claude Code design patterns to build a good search agent. Cheat at Search Essentials continuesTuesday + Thursday, 12PM - https://maven.com/lls/5c240bโ โCheat at Search Essentials teaches the basics of search + retrieval. It assumes zero context, catching you up on decades of search and Information Retrieval. You can watch the recording of Friday's class. This week I'll teach about Embeddings + Vector Search (Tuesday) and Search Evaluation (Thursday). Come to both or just one! Where search teams go wrong in 2026Friday, 12PM - https://maven.com/p/aa3d9c/where-are-teams-going-wrong-with-searchโ I'll be chatting with Trey Grainger, author of AI Powered Search. We'll discuss the mistakes we see search teams make in 2026. Either chasing the wrong hype (or not chasing the correct hype!). We'll also contrast trainings - the Cheat at Search course vs AI Powered Search. Bring your questions! --------- All leading up to: Cheat at Search w/ Agents starts in one week!We're watching a search inflection point - as consequential as the introduction of embeddings. When agents, not rerankers, drive relevance we need to rethink how we work as search practitioners. Guest speakers from IBM, Sid.ai, Hornet, and LightOn to help us think through how search is being changed. Signup here - http://maven.com/softwaredoug/cheat-at-search - use code search-tips. -Doug โSlack Community * Events ยท Consulting ยท 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: |
Doug Turnbull
I share search tips, blog articles, and free events I'm hosting about the search+retreval industry, vector databases, information retrieval and more.
I'm writing about the weak spots in vector databases. Where you should prod and poke when selecting a vendor. Today: Updating Vector Databases If you think about the old vector search regime, it involved Indexing everything up front Never updating the index Search-only We overindexed on this paradigm, creating data structures focused on good search performance that couldn't tolerate updates. I wrote about how sensitive graph-based vector DBs in particular are to updates, picking on Lucene...
Hey all, I wrote a new article about a technique that has come up over and over in my work, especially in my Cheat at Search training, for doing effective query understanding into a large vocabulary. Instead of asking an LLM to classify into a vocabulary. Ask it to hallucinate fake entities, then resolve those to real ones client side. Save yourself a lot of tokens and use cheaper models. https://softwaredoug.com/blog/2026/08/10/hypothetical-classifications -Doug PS - A reminder that Vectors...
There's a class of search problems where: The total number of records is small ~1 million The index is built up front and doesn't change frequently Don't get hoodwinked into buying a vector database. Just brute-force search your embeddings. A naive Numpy search can do exhaustive vector search at 170QPS. You can replicate and copy that data to scale even further. More in my blog article: https://softwaredoug.com/blog/2026/07/29/just-brute-force-embeddings Wectors Week + Context Camp A reminder...