Prompt engineering plays a crucial role in maximising the potential of generative AI. It is not limited to the mere creation and formulation of prompts, it encompasses a diverse array of skills and techniques.

What are prompts?

Prompts are input elements such as words, phrases, questions, or keywords that users enter into generative AI tools to produce results. Prompt engineering is the skill of crafting highly effective prompts to achieve the desired outcomes.

In the context of tools such as RMIT’s Val and OpenAI’s ChatGPT, prompts refer to the instruction or discussion topic that users provide for the AI tool to respond to. Prompts can take the form of a question, statement, or any stimulus aimed at fostering creativity, reflection, or engagement.

What makes a good prompt?

Firstly, when using AI tools like Val, Google Gemini and Adobe Firefly, the better your prompts, the better the results you’ll get. Simply put, an effective prompt not only sets the topic but also provides clear instructions on the task, effectively guiding the AI.

Creating effective prompts can be a challenging task, as the quality of the output relies on the specificity and clarity of the prompts or input instructions. This module will help you to create effective prompts for learning.

Principles for good prompting

1. Craft precise and unambiguous instructions.
2. Use the conversational interface on many generative AI tools to refine the outputs.

Specificity is key! The tool will make an assumption on any point you don’t clearly explain.

Try and refine

There is no hard science to good prompting. Instead, approach it as a process of trial and error:

1. Formulate a relevant prompt.
2. Consider when the completions fall short of expectations.
3. Enhance the clarity of the prompt. You could refine your prompts using a set of exemplars, such as the ones found in this module.
4. Repeat the process to iteratively improve your prompt’s effectiveness.

Remember that as you chat with generative AI, the tool will learn more about what you need. Use the conversational turns to help the AI improve its outputs.

The structure of a good prompt

A good prompt has 4 key elements: Role, Task, Requirements and Instructions.

Let’s take a look at each one in depth.

Role

Prompts starting with “act as…” or “you are a…” will provide responses similar to that of the role which you provide. Setting a specific role for a given prompt increases the likelihood of more accurate information, when done appropriately. You may need to experiment with the role wording to get the best output from different generative AI tools.

E.g.:

• act as an expert in the field of computer science
• you are a university lecturer in psychology

Setting a role determines the type of information and the way the information is communicated to you, and also determines the interactivity of the conversation.

Task

The task is a summary of what you want the prompt to do. There is a lot of creativity that comes into writing a great task. It can range from generating birthday gift ideas to creating game show questions with the content from your last lecture.

• Outline what you want the AI tool to do.
• Be specific about the task’s objective.

Requirements

Writing clear requirements is all about giving as much information as possible to ensure your response doesn’t use any incorrect assumptions. AI tools make assumptions for any information they don’t have in the prompt. 

• It is often important to define what an output should look like and conditions that affect the output.
• This includes the various conditions to limit the assumptions made by the tool.

Instructions

Instructions will inform the AI tool how to complete the task. Instructions can include examples of how it is supposed to work, steps it can follow or other relevant information.

• How should the AI tool go about completing its task.
• Examples of how it could go about tasks.
• Feedback on steps it has taken will improve this even further.