AI Tools Best Practices Starter Pack

What we verified before publishing

AI-generated content may contain mistakes. Check the sources below before relying on important information.

The following claims were verified through Perplexity Sonar before the questions were finalised. The host can reference any of them during play:

• A prompt is the input provided to an AI model to elicit a specific response, ranging from simple questions to complex instructions.
• Prompt engineering is the practice of designing and refining inputs to guide AI models toward generating more accurate and relevant outputs.
• Zero-shot prompting is a technique where an AI is asked to perform a task without being provided any example inputs or outputs in the prompt.
• Large language models (LLMs) are neural networks trained on vast amounts of text data to understand and generate human-like language.
• AI hallucinations occur when a model generates information that appears plausible and coherent but is factually incorrect or ungrounded.
• Human-in-the-loop (HITL) is an approach where humans review, approve, or correct AI outputs at critical decision points to ensure accuracy and safety.
• Data minimization is a privacy best practice that involves sharing only the information strictly necessary for the AI to perform its intended task.
• Users should avoid inputting sensitive, confidential, or proprietary data into public-facing AI systems to prevent potential exposure.
• Providing context, such as a specific role or background information, helps AI models generate more tailored and useful responses.
• Iterative refinement, or testing and adjusting prompts based on AI responses, is a core strategy for improving the quality of AI-generated content.