From 2623698844b971db7eadec52ea5e866c5e7ca516 Mon Sep 17 00:00:00 2001
From: Mano Toth <mano@axiom.co>
Date: Fri, 5 Dec 2025 12:18:40 +0100
Subject: [PATCH] Fix AI Eng Evaluate overview

---
 ai-engineering/evaluate/overview.mdx | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/ai-engineering/evaluate/overview.mdx b/ai-engineering/evaluate/overview.mdx
index c72df061..766d23ed 100644
--- a/ai-engineering/evaluate/overview.mdx
+++ b/ai-engineering/evaluate/overview.mdx
@@ -26,7 +26,7 @@ Axiom's evaluation framework follows a simple pattern:
 
 <Steps>
 <Step title="Create a collection">
-Build a dataset of test cases with inputs and expected outputs (ground truth). Start small with 10-20 examples and grow over time.
+Build a set of test cases with inputs and expected outputs (ground truth). Start small with 10-20 examples and grow over time.
 </Step>
 
 <Step title="Define scorers">