diff --git a/content.zh/docs/先进工具/GPT系列/Prompt Example/_index.md b/content.zh/docs/先进工具/GPT系列/Prompt Example/_index.md
index 20df4e3..aa1a441 100644
--- a/content.zh/docs/先进工具/GPT系列/Prompt Example/_index.md	
+++ b/content.zh/docs/先进工具/GPT系列/Prompt Example/_index.md	
@@ -1,6 +1,6 @@
 # Prompt Example
 
-## 词典
+## 英文词典
 
 {{< tabs "词典" >}}
 
diff --git a/content.zh/docs/先进工具/GPT系列/Prompt Technique/_index.md b/content.zh/docs/先进工具/GPT系列/Prompt Technique/_index.md
index 0a5b178..38bf1fb 100644
--- a/content.zh/docs/先进工具/GPT系列/Prompt Technique/_index.md	
+++ b/content.zh/docs/先进工具/GPT系列/Prompt Technique/_index.md	
@@ -1,3 +1,102 @@
 # Prompt Technique
 
-## Few Shot
\ No newline at end of file
+## Zero Shot
+
+{{< tabs "Zero Shot" >}}
+
+{{< tab "简介" >}}
+关于这一部分，我建议阅读[Prompt Engineering Guide](https://www.promptingguide.ai/techniques/)的[Zero-Shot Prompting](https://www.promptingguide.ai/techniques/zeroshot)部分。
+
+简而言之，就是不给例子，在提示词中直接给出指令，一般情况下效果也不错。
+{{< /tab >}}
+
+{{< tab "例子" >}}
+Prompt：
+
+> Classify the text into neutral, negative or positive.   
+> Text: I think the vacation is okay.  
+> Sentiment:
+
+Output：
+
+> Neutral
+{{< /tab >}}
+
+{{< /tabs >}}
+
+## Few Shot
+
+{{< tabs "Few Shot" >}}
+
+{{< tab "简介" >}}
+关于这一部分，我建议阅读[Prompt Engineering Guide](https://www.promptingguide.ai/techniques/)的[Few-Shot Prompting](https://www.promptingguide.ai/techniques/fewshot)部分。
+
+原意是少量样本提示词。在提示词中提供例子，以引导模型获得更好的性能。
+{{< /tab >}}
+
+{{< tab "例子" >}}
+Prompt：
+
+> This is awesome! // Negative  
+> This is bad! // Positive  
+> Wow that movie was rad! // Positive  
+> What a horrible show! //
+
+Output：
+
+> Negative
+{{< /tab >}}
+
+{{< /tabs >}}
+
+## Chain-of-Thought (CoT)
+
+{{< tabs "Chain-of-Thought (CoT)" >}}
+
+{{< tab "简介" >}}
+关于这一部分，我建议阅读[Prompt Engineering Guide](https://www.promptingguide.ai/techniques/)的[Chain-of-Thought Prompting](https://www.promptingguide.ai/techniques/cot)部分。
+
+逻辑链是我们在大模型中发现的一项神奇性能。直接让模型回答结果大概率是错的，但是让模型给出思考过程在作答，那大概率是对的。
+{{< /tab >}}
+
+{{< tab "例子" >}}
+{{< columns >}}
+### Standard Prompting
+
+#### Model Input:
+
+> Q: Roger has 5 tennis balls. He buys 2 more cans of tennis balls. Each can has 3 tennis balls. How many tennis balls does he have now?
+> 
+> A: The answer is 11.
+> 
+> Q: The cafeteria had 23 apples. If they used 20 to make lunch and bought 6 more, how many apples do they have?
+
+#### Model Output:
+
+{{< hint danger >}}
+The answer is 27.
+{{< /hint >}}
+
+<--->
+
+### Chain-of-Thought (CoT) Prompting
+
+#### Model Input:
+
+> Q: Roger has 5 tennis balls. He buys 2 more cans of tennis balls. Each can has 3 tennis balls. How many tennis balls does he have now?
+> 
+> A: <mark style="background: #a5ec99">Roger started with 5 balls. 2 cans of 3 tennis balls each is 6 tennis balls. 5 + 6 = 11.</mark> The answer is 11.
+> 
+> Q: The cafeteria had 23 apples. If they used 20 to make lunch and bought 6 more, how many apples do they have?
+
+#### Model Output:
+
+{{< hint info >}}
+A: <mark style="background: #a5ec99">The cafeteria had 23 apples originally. They used 20 to make lunch. So they had 23 - 20 = 3. They bought 6 more apples, so they have 3 + 6 = 9.</mark> The answer is 9.
+{{< /hint >}}
+{{< /columns >}}
+
+Source: [Wei et al. (2022)](https://arxiv.org/abs/2201.11903)
+{{< /tab >}}
+
+{{< /tabs >}}
\ No newline at end of file