diff --git a/omp-docs/agentic-web-research/searxng-tuning.md b/omp-docs/agentic-web-research/searxng-tuning.md
index 4724e68..ebc8b27 100644
--- a/omp-docs/agentic-web-research/searxng-tuning.md
+++ b/omp-docs/agentic-web-research/searxng-tuning.md
@@ -15,11 +15,12 @@ resource: https://docs.searxng.org
 
 # SearXNG Tuning
 
-SearXNG is a metasearch engine. It aggregates hundreds of upstream search
-services into one result set (upstream `settings.yml` defines 388 engine
-entries at master, probed 2026-10-19; the live fleet instance loads 262).
-Configuration lives in `settings.yml`. The recommended deployment is Docker
-Compose (or Podman Quadlet) with a Valkey container.
+SearXNG is a metasearch engine: it aggregates upstream search services into one result set.
+Upstream ships several hundred engine entries (385 in `settings.yml` at master, read
+2026-10-21 — the count drifts every week, so treat it as an order of magnitude, not a fact);
+what your instance actually loads is what `/config` reports, and the fleet's loads **262**
+(re-read 2026-10-21). Configuration lives in `settings.yml`. The recommended deployment is
+Docker Compose (or Podman Quadlet) with a Valkey container.
 
 This page lists the settings that matter for speed, privacy, and useful results.