diff --git a/apps/ai-game-creator-shell/src-tauri/src/ui_editor/commands/recognition.rs b/apps/ai-game-creator-shell/src-tauri/src/ui_editor/commands/recognition.rs
index 49750b04e..c95a4c781 100644
--- a/apps/ai-game-creator-shell/src-tauri/src/ui_editor/commands/recognition.rs
+++ b/apps/ai-game-creator-shell/src-tauri/src/ui_editor/commands/recognition.rs
@@ -44,13 +44,13 @@ const SYSTEM_PROMPT: &str = r#"
 * 由于每个截图未必是完整的,   可能是局部的,  每棵树描述清楚每个截图上UI的层次结构即可
 * 不同树的共用框架/层次/...请使用使用相同的名称描述.  不同状态/变体名称使用相同的前缀, 用后缀区别
 * 粒度要求: 尽可能细致, 以可交互,方便程序化控制的最小单位为准. 包括不限于: icon, 进度条的底槽、填充和外框; slider的底槽, dragger等.
- * 为每个节点直接返回 component.
+* 为每个节点直接返回 component.
   无背景的逻辑容器返回 "PureNode"，不要返回 null.
   有背景的容器推荐使用Simple+不锁定宽高比的Image component.
   目前我们只做识别, 不要求图片字体参数.
   每个节点最多返回一个 component；需要多个视觉层时拆成多个节点。
   文字组件要求: 艺术字等作为图片组件, 其余正常文字要作为单独的节点识别.
-
+* 不鼓励兄弟节点相互重叠, 对于背景等元素, 请promote为父节点的组件, 不要再建单独的兄弟节点承载.
 "#;
 
 #[derive(Clone, Debug, Deserialize, PartialEq, Serialize, JsonSchema)]
diff --git a/apps/ai-game-creator-shell/src-tauri/src/ui_editor/commands/separation/prompt.rs b/apps/ai-game-creator-shell/src-tauri/src/ui_editor/commands/separation/prompt.rs
index 95dd80ef4..a91a94889 100644
--- a/apps/ai-game-creator-shell/src-tauri/src/ui_editor/commands/separation/prompt.rs
+++ b/apps/ai-game-creator-shell/src-tauri/src/ui_editor/commands/separation/prompt.rs
@@ -35,10 +35,6 @@ pub(super) fn gen_binding_prompt(nodes: Vec<&SeparationNode>) -> String {
     let binding_system_prompt = format!(
         r#"
   You will be given a src UI design image and a processed image, where some ui elements are separated.
-  Here were the separation requirements:
-  ```
-  {SHARED_SEPARATION_REQ}
-  ```
   You need to recognize and review the separation using the given tool.
   field notes:
     * extracted_area MUST be the recognized area from the processed image, INSTEAD OF from the src image.
@@ -47,6 +43,20 @@ pub(super) fn gen_binding_prompt(nodes: Vec<&SeparationNode>) -> String {
       Do not copy, infer, or reuse the source node rectangle.
       The src image is only for identifying which semantic UI element belongs to to_node.
 
+  Here were the separation requirements:
+  ```
+  {SHARED_SEPARATION_REQ}
+  ```
+  And you should also review if the extracted's successfully meet the src image:
+    * shape
+    * color
+    * style
+    * edge process
+    ...
+
+  if not, use `NeedRework` data structure in the tool to indicate the (it should be from which) node id and advice.
+  your advice (less than 20 words) will be used to improve the separation in the next time.
+
   these node need handle:
   "#
     );