# Advanced Prompting Techniques
Effective prompting is the key to getting the best results from Gemini CLI. This guide will teach you advanced techniques to craft prompts that produce accurate, relevant, and useful responses.
## Understanding Prompt Structure
A well-structured prompt typically includes:
1. **Context**: Background information
2. **Task**: What you want the AI to do
3. **Format**: How you want the output structured
4. **Constraints**: Any limitations or requirements
## Technique 1: Chain of Thought Prompting
In the Gemini CLI interactive session, encourage step-by-step reasoning:
```
> Let's think step by step. How would you solve this math problem: If a train travels 120 miles in 2 hours, what's its average speed?
```
## Technique 2: Role-Based Prompting
Assign a specific role to the AI:
```
> You are a senior software engineer. Review this code and suggest improvements: [code here]
```
## Technique 3: Few-Shot Learning
Provide examples to guide the response:
```
> Translate these phrases to French:
English: Hello, how are you?
French: Bonjour, comment allez-vous?
English: Thank you very much
French: Merci beaucoup
English: Where is the library?
French:"
```
## Best Practices
1. **Be Specific**: Vague prompts lead to vague responses
2. **Use Clear Language**: Avoid ambiguous terms
3. **Set Context**: Provide relevant background information
4. **Specify Format**: Tell the AI how to structure the output
5. **Iterate**: Refine your prompts based on results
## Common Pitfalls to Avoid
- Being too vague or too verbose
- Not providing enough context
- Asking multiple unrelated questions in one prompt
- Forgetting to specify the desired output format
Continue practicing these techniques to master the art of prompting!