Definition: Foundational background (domain data, goals, context) the model needs for accuracy and relevance.
Low Context: OK for simple, general queries where ambiguity is low.
Medium Context: Provide essential background to avoid misinterpretation.
High Context: Use detailed, domain-specific input or examples.
Why? More context improves relevance and precision for complex queries.

Definition: Structural cue (e.g., table, list, summary) defining how the answer should appear for readability and workflow efficiency.
Low Output Focus: Default formatting is acceptable.
Medium: Provide a specific structure like a list or short table.
High: Require detailed structure—such as JSON, outline, or nested sections.
Why? Structure guides the AI to produce usable formats for downstream use.

Definition: The specific action or function the AI is being asked to do (e.g., generate ideas, summarize, explain, compare).
Low Task Clarity: General task description (e.g., "Write about climate").
Medium: Include goal and constraints (e.g., "Summarize climate risks in 5 bullet points").
High: Detailed and precise with clear boundaries (e.g., “Compare U.S. vs. China emission trends in under 100 words using 2023 data”).
Why? Clear tasks reduce hallucinations and increase usable output.

Definition: Any rules or limits the AI must follow, such as tone, length, exclusions, or vocabulary.
Low Constraint: No limits; open tone and style.
Medium: Some direction (e.g., use simple language, keep it formal).
High: Specific directives (e.g., "under 50 words, no technical jargon, persuasive tone").
Why? Constraints sharpen focus and align outputs with intended use or audience.