[Back to Course](/en/courses/prompt-engineering) Lessons

# Prompting Fundamentals

Learn the basic techniques for crafting effective prompts for AI language models.

## The Art of Prompting

A prompt is the instruction you give to an AI model. The quality of your output depends heavily on how well you frame your input.

### Basic Techniques

-   **Zero-Shot Prompting**: Ask directly without examples. Best for simple, well-defined tasks.
-   **Few-Shot Prompting**: Provide a few examples before asking. Improves accuracy for specific formats or styles.
-   **Chain-of-Thought**: Ask the model to reason step by step. Ideal for complex problem-solving.

### Best Practices

-   Be specific and clear about what you want.
-   Provide context and constraints.
-   Define the output format (bullet points, JSON, table, etc.).
-   Iterate and refine based on results.

### Example: From Basic to Refined

**Basic**: “Write a summary of our quarterly report.”

**Refined**: “Write a 3-paragraph executive summary of our Q3 2025 financial report. Focus on revenue growth, cost reductions, and key risks. Use professional tone. Output as plain text.”