diff --git a/rag/README.md b/rag/README.md
index 511fa0f..f006cf9 100644
--- a/rag/README.md
+++ b/rag/README.md
@@ -32,8 +32,12 @@ Every file has YAML frontmatter (`doc`, `title`, `keywords`, `summary`) for rank
 - **Keyword retrieval (built-in):** run `./search.sh <terms>` — a dependency-free
   ripgrep/grep ranker over the corpus (frontmatter `keywords` weighted ×3 + body),
   printing ranked docs with the matching `##` section headers. No index to build.
-  e.g. `./search.sh session token csprng` → `06-security.md §2`. `INDEX.md` is the
-  hand-curated routing table; a bluge/embeddings index can ingest the same `.md` files.
+  e.g. `./search.sh session token csprng` → `06-security.md §2`.
+- **bluge full-text index (KWONDoc):** this corpus is indexed into KWONDoc's bluge
+  index (`~/.kwondoc/search-index`, category `five-rag`) so `bluge_search` finds it.
+  Re-index after edits: `cd ~/kwondoc && go run ./cmd/ragindex <abs path to rag> five-rag`
+  (online upsert — keyed by file path, does not wipe other docs).
+- `INDEX.md` is the hand-curated routing table; an embeddings index can ingest the same `.md`.
 - **Embedding RAG:** chunk by `##` headers (each section is self-contained). Frontmatter
   `summary` makes a good chunk preamble.