diff --git a/website/blog/2024-11-15-CaptainAgent/index.mdx b/website/blog/2024-11-15-CaptainAgent/index.mdx
index 70e8316c46..a71a2b63ff 100644
--- a/website/blog/2024-11-15-CaptainAgent/index.mdx
+++ b/website/blog/2024-11-15-CaptainAgent/index.mdx
@@ -14,7 +14,7 @@ tags: [LLM, GPT, AutoBuild]
 
 # Introduction
 
-Assembling a team of LLM agents is easy, but dynamically choosing the right agents into a group chat according to the task is hard. In this blog, we introduce **CaptainAgent**, an agent that can automatically build a team of agents to fulfill diverse, complex task requirements.
+Given an ad-hoc task, dynamically assembling a group of agents capable of effectively solving the problem is a complex challenge. In many cases, we manually design and select the agents involved.  In this blog, we introduce **CaptainAgent**, an intelligent agent that can autonomously assemble a team of agents tailored to meet diverse and complex task requirements.
 We design a two-step workflow for CaptainAgent to build a high quality team and solve the problem:
 - (**Step 1**) CaptainAgent will first identify a subtask instructed by our prompt, list several roles needed for this subtask, and then create a team of agents accordingly by retrieval, selection, and generation. Each of these will be equipped with predefined tools retrieved from the tool library.
 ![Building workflow](img/build.png)