Artificial Intelligence (AI): It’s a program made by people that makes computers do things that seem intelligent (or smart) in the same way that humans are intelligent.

AI tool: Software that can automate or assist users with a variety of tasks

Algorithm: A set of rules or steps a computer follows to solve a problem or make a decision.

Bias: When an AI system makes unfair decisions because it learned from unbalanced or incomplete data.

Chatbot: AI software designed for natural language conversations.

Data: Information that AI uses to learn, like what videos you watch or what words you say.

Deepfake: Images, videos, or audio that are edited or generated using AI tools, and that may depict real or non-existent people. 

Generative AI: AI that can create new things like images, music, or text.

Hallucination: Instances where AI generates plausible but inaccurate, incorrect, or nonsensical answers.

Large Language Model (LLM): A type of AI model trained on vast amounts of text data, capable of understanding and generating human-like text across a wide range of topics and tasks. 

Machine Learning: A way for AI to improve over time by learning from data.

Pattern Recognition: AI’s ability to find similarities or trends in data.

Prediction: A guess made by an AI system based on patterns in data e.g., recommending a movie you might like or guessing what word you’ll type next.

Prompt: Text input or instruction given to an AI model to guide or initiate the generation of specific content or responses. 

Token: A small chunk of text (like a word, part of a word, or punctuation mark) that AI systems use to understand and generate language. For example, the sentence “What time is it?” is split into tokens “What”, “time”, “is”, “it”, and “?”.

The CLEAR method is a framework used in prompt engineering to improve the accuracy, relevance, and quality of AI-generated responses. While different industries sometimes apply slight variations, the most widely recognized version (developed by L.S. Lo in 2023) focuses on five core principles: Context, Language, Expectations, Actions, and Results. 

Context

Provide the "Why" and the "Who." Tell the AI what its role is and what the background of the situation is.

• Prompting tip: Start with "Act as a..." or "You are an expert in..."

• Example: "You are a senior marketing strategist. We are launching a new eco-friendly water bottle aimed at urban professionals."

Language

Define the tone, style, and complexity of the response. This ensures the output matches your intended audience.

• Prompting tip: Use adjectives like clinical, persuasive, formal, or empathetic.

• Example: "Use a professional yet inspiring tone. Avoid jargon, but keep the language sophisticated."

Expectations

State the specific goals or constraints. What must be included, and what must be avoided?

• Prompting tip: Be direct about the "must-haves." in the answer you want.

• Example: "The output must highlight the BPA-free materials and the 24-hour cold-retention feature. Do not mention competitor brands."

Actions

This is the "Ask." What exactly do you want the AI to do with the information provided?

• Prompting tip: Use strong command verbs like analyze, draft, categorize, or brainstorm.

• Example: "Draft three different social media captions for an Instagram launch post."

Results

Describe the final format. Do you want a table, a list, a code block, or a specific word count?

• Prompting tip: Specify the structure to save time on re-formatting later.

• Example: "Present the results in a table.'"