Keynote: The Next Generation of Enterprise Search: Intent‑Aware, Hybrid, and Open
summary
Argues enterprise search needs intent-aware systems built around query intent, journey intent, product intent, mixing lexical and semantic methods rather than vector‑only stacks. Shows a German manufacturing POC that solves ~80% of relevance for ~10% of previous cost while the remaining 20% needs semantic models. Recommends OpenSearch features—hybrid retrieval, dynamic relevance, observable explainable pipelines—plus tooling (relevancy workbench, launchpad), better AB testing, vector agility RFCs and tiered storage to cut latency and cost at data scale.
AI-written summary · about
chapters (15)
- 0:00Next-gen enterprise search intro
- 1:22The data swamp challenge
- 3:05Beyond traditional results
- 4:49Vector search limits
- 7:17Query intent for better results
- 9:23Lexical vs semantic search
- 10:48User decision paths
- 12:54Product findability trade-offs
- 15:44Search as product metrics
- 16:47Agent builders and vector refugees
- 20:59Vector search balance
- 22:43Hybrid search defined
- 23:44Vector search adaptability
- 24:46Data scale challenges
- 25:50Intent and confidence closing
related talks
41mKeynote: From Keyword Search to Vector Powered Insights: Th...
38mAI-Ready Data Foundation Using Amazon OpenSearch
41mWhat you see is what you mean; intent based ecommerce search
30mBeyond Keywords: Building an AI-Powered Search That Reads Your Mind
47mBoosting AI With OpenSearch: Vector Stores, Similarity Search, and Retrieval-Augme...
06mSponsored Keynote: OpenSearch - See Everything: Open Observability for Agentic AI
44mRediscover your keyword search: Expand, Enrich and Rewrite
22mAgentic Hybrid Retrieval: Orchestrating LLM Agents, Hybrid Search & Explainability in OpenSearch