From 07ac3157515fa1cd7d4e65b864a124df647060a6 Mon Sep 17 00:00:00 2001
From: tobi <tobi@noreply.forgejo.corentic.eu>
Date: Wed, 1 Jul 2026 09:33:02 +0000
Subject: [PATCH] Update README.md

---
 README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 422a8e8..315f8c0 100644
--- a/README.md
+++ b/README.md
@@ -13,7 +13,7 @@ When an LLM agent needs to follow these conventions, it usually has two bad opti
 
 Dervish replaces both with a **one-call MCP tool**: pass your sequences, get back a ~60-token grammar. A rule you can trust, at a fraction of the cost.
 
-**Without Dervish:** token cost scales linearly with examples. **With Dervish:** one compact grammar describes them all — a ~60–200 token rule instead of thousands of tokens of raw examples.
+**Without Dervish:** token cost scales linearly with examples. **With Dervish:** one compact grammar describes them all — a ~60–200 token rule instead of thousands of tokens of raw examples. Try it out and you too will say:
 
 <p align="center"><img src="dervish.gif" alt="Dervish animation" width="37.5%"></p>