Notes on plan-conditioned search, the latency budget of agentic retrieval, and source-aware ranking.https://slorg.skelfresearch.com/en-ushttps://slorg.skelfresearch.com/blog/source-aware-retrieval/https://slorg.skelfresearch.com/blog/source-aware-retrieval/Most search engines hide their backends behind a single answer. slorg shows you which engines returned which URLs, what content was actually extracted, and what the LLM scored each one — because retrieval without source awareness is just confident guessing.Wed, 12 Nov 2025 00:00:00 GMThttps://slorg.skelfresearch.com/blog/latency-budget-of-planning/https://slorg.skelfresearch.com/blog/latency-budget-of-planning/A breakdown of the three LLM calls and N content fetches that make up a slorg query, what each one costs, and which knobs actually move the needle.Thu, 09 Oct 2025 00:00:00 GMThttps://slorg.skelfresearch.com/blog/agentic-search-google-and-prays/https://slorg.skelfresearch.com/blog/agentic-search-google-and-prays/Why the dominant pattern in LLM-mediated search is functionally a wrapper around a single search call — and what changes when you make the plan the first artifact, not the last.Sun, 14 Sep 2025 00:00:00 GMT