RAG Isn't Dead: Navigating Retrieval vs. Agentic Search
hugobowne · x · 2026-08-27
Addressing the notion that "RAG is dead" and agents just need grep, the author argues that RAG, embeddings, BM25, chunking, and agentic search solve distinct retrieval problems. Knowing when to use each is becoming a core skill for building useful agents. The final session of Context Camp, taught by search expert Doug, will explore classic RAG's place in the retrieval landscape, its mechanics, and when it remains superior to simple grep, specifically examining the boundary between Q&A and agentic search.
More from coding & agent
- Optimizing inference on 4090: sub-10ms latency achieved — yacineMTB · 2026-08-27
- Tutorial request: Bulk downloading songs with AI agents and auto-tagging — EnvironmentalTry8353 · 2026-08-27
- Google AI Studio enables two-way GitHub sync with direct commits and one-click deploy — jackwoth · 2026-08-27
- Opinion: Notification systems need rebuilding for agent-primary usage and context linking — andreisavu · 2026-08-27
- OpusClip and Beehiiv integrate to auto-turn videos into newsletters via Claude — azed_ai · 2026-08-27
- Bixbench3: Frontier Agents Score Below 50% in Reproducing Paper Analysis — xeophon · 2026-08-27