Data Training Courses

Home | Power BI | Excel | Python | SQL | Generative AI | Visualising Data | Analysing Data

Use AI tools Effectively

Generative AI tools are useful to us today. They can help us do some tasks better and other tasks quicker. AI tools, such as large language models, have been trained to provide relevant helpful responses to any questions we may pose to them. For example, they can:

• they can answer a question with useful relevant information,
• provide step-by-step instructions for a task, such as making an omelette
• draft a letter with the right tone and style, such as creating a job description
• review and suggest improvements to a document or text,
• brainstorm ideas on a topic, for example, suggest possible titles for a spy novel
• and explain a complex topic like CRISPR gene editing
• and summarise a document or set of web pages, such as this review.

Take care when using AI tools

AI tools have weaknesses as well as considerable strengths. Here are the three points to bear in mind:

1. AI tools can make mistakes. And when they do lie to us, they do it very convincingly and confidently. Always check any important results independently.
2. AI tools remember and learn from every prompt. Never put any confidential information into AI tools. Keep your data private.
3. AI tools have learnt from everything on the internet: all the amazing, wonderful content but also some undesirable stuff. They have “guard rails” in place but they are capable of generating harmful content or exhibiting bias so review their output carefully!

Tips to get better responses from AI tools

We talk with AI tools by providing a question or instruction (called a prompt). The AI tool responds and then we can prompt again and the AI tool will respond again – and so on. A basic instruction alone may not result in a good response. We can help AI tools help us with more relevant, accurate responses if we provide more tailored prompts. Here are a few pointers to obtain better responses from AI tools.

• Make the instruction more specific.
• Tell GPT what role you want it to play.
• Provide context and relevant background.
• Describe any constraints.
• Provide an example of the response required.
• Refine your prompt and continue the conversation.
• Create a new chat and ask a new question on a different topic.

The RICE Framework

One framework to help us with this is RICE: this stands for Role, Instructions, Context (and Constraints) and Examples.

• Role: ask the AI tool to act in a certain role e.g., an expert travel advisor, and tell it how to respond e.g. brief or verbose, friendly or formal. Also, for example, tell the AI tool to provide a link to a relevant web page with each response.
• Instructions: provide specific, concrete instructions to the AI tool. (This is the most important piece of advice.)
• Context (and constraints): provide background information that will help the AI tool tailor its response.
• Example: provide an example of the sort of response that we would like to see.

Knowledge Check

What is the difference between an AI tool and the BBC Radio 4 show ‘The Unbelievable Truth’?

1. They are both hosted by David Mitchell.
2. AI tools may hide a few lies in a a largely truthful response whereas the show hides a few truths in a sea of lies.
3. This is a stupid question: we cannot compare an AI tool with a radio show.