AI: AI literacy

Do you know about the capabilities and limitations of the AI you are using? 

Generative AI tools, for example, can create new content based on patterns in the data they were trained on including writing text, brainstorming ideas and explaining concepts. Limitations include concerns about accuracy and bias, hallucinations and a lack of reasoning and comprehension in responses. Any information you enter may be stored or used to improve the tool so you need to think carefully about the data you input. 

A prompt is the input given to an AI model to elicit a response. It can be a question, statement, or any text that directs the AI on the desired output. The quality and clarity of the prompt can greatly affect the relevance and accuracy of the AI's response. 

Here are some general principles to use when prompt writing to help ensure that the AI you are using generates accurate, relevant and useful responses.   

• Be Clear and Specific: Clearly define the task or question and avoid ambiguous language 

• Provide Context: Include relevant background information to guide the AI 

• Set Expectations: Indicate the format or style of response you want and mention any specific requirements 

• Keep It Concise: Avoid long or complex prompts by focusing on essential information 

• Iterate and Refine: Test and adjust prompts based on the AI’s responses 

• Consider the Audience: Tailor the prompt to the intended audience’s knowledge level using appropriate vocabulary 

Prompt Frameworks provide a structured approach to writing effective AI prompts and help the AI understand your request. Here are some examples of frameworks you could use.  

Google 5-step method (TCREI) 

Task: What do you want the AI to do. Specify a persona or format. 

Context: Provide necessary details to refine the output

References: Include examples to guide the AI's response

Evaluate: Did the input you provided give you the output you needed? 

Iterate: Experiment, try again, adjust your prompt, add more information 

The CO-STAR framework 

Context: Why do I want the model to do that? 

Objective: What do I want it to do? 

Style: In what style should it write? 

Tone: How is the emotion and sentiment conveyed? 

Audience: Who is the recipient? 

Response: How should the model's answer be structured?

 It is important to treat information from AI tools in the same way you do any academic source.

• Always cross-check AI generated content with peer-reviewed and reputable sources
• Check any citations provided by AI - make sure they are accurate and that they actually exist
• Check for any biases, stereotypes and unfair generalisations
• Consider other perspectives 

Here are some useful questions to ask yourself before relying on content generated by AI: 

• Is the information reliable and accurate? 
• Does it align with trusted academic sources?
• Have I critically appraised the output or am I relying too heavily on AI? 
• Could I confidently explain this work with the help of AI? 

This is about the role of humans in how AI is developed, used and evaluated. 

What does this mean for you? 

Ensure you stay in control - use AI tools to help with tasks but not to make decisions for you. 

Remember - your judgement matters!  AI can suggest ideas, summarise texts and generate content but it doesn't understand the context, ethics or academic expectations like you do. You are responsible for work you submit or share and academic integrity and fairness still apply. 

AI should support but not replace, human creativity, learning and responsibility. 

See the following page for information about ethical and responsible use of AI. 

Using AI ethically