Guides

Prompt Engineering

Effective prompts are the key to getting great results from Cortiqa models. This guide covers techniques for writing clear, specific, and effective prompts.

Core Principles

• Be specific: Tell the model exactly what you want, including format, length, and style
• Provide context: Include relevant background information
• Use examples: Show the model what good output looks like (few-shot prompting)
• Set constraints: Define boundaries and requirements clearly
• Iterate: Refine your prompts based on outputs

Techniques

Zero-shot

Give the model a task with no examples:

Classify the following text as positive, negative, or neutral:

"The product works well but shipping was slow."

Sentiment:

Few-shot

Provide examples of desired input-output pairs:

Classify sentiment:

Text: "I love this product!" -> positive
Text: "Terrible experience." -> negative
Text: "The product works well but shipping was slow." ->

Chain of Thought

Ask the model to think step-by-step:

Solve this problem step by step:

A store has 45 apples. They sell 12 in the morning and receive a shipment of 30. 
How many apples do they have now?

Let me think through this step by step:

Examples

See our System Prompts guide for more advanced techniques including role-playing, output formatting, and multi-step workflows.

Common Mistakes

• Too vague: “Write something about AI” vs “Write a 200-word blog introduction about how small businesses can use AI for customer service”
• No format specification: Always specify the desired output format (JSON, markdown, list, etc.)
• Contradictory instructions: Ensure all parts of your prompt are consistent
• Ignoring temperature: Use lower temperature (0.0-0.3) for factual tasks, higher (0.7-1.0) for creative tasks