Topic 1: Prompting & Prompt Engineering 101: Quick overview
Prompting & Prompt Engineering 101: Quick overview
Every time you ask an AI tool to do something, you are giving it a prompt.
A prompt could be a simple question such as “What is a product roadmap?” or a much more detailed instruction asking AI to analyse customer feedback, review requirements or create user stories.
The important thing to understand is that what you give the AI influences what you get back. This is where prompting and prompt engineering become useful skills for Product Managers and Business Analysts.
What is a Prompt?
A prompt is simply the instruction, question or information you give to an AI.
For example:
“Summarise these customer interview notes and identify the five most common problems.”
That is a prompt.
But prompts can also include much more information, such as the product you are working on, who your users are, the business objective, constraints, examples and the format you want the answer in.
The more the AI understands what you are trying to achieve, the better chance it has of producing something useful.
What is Prompt Engineering?
Prompt engineering is the practice of designing, testing and improving prompts to get better results from AI.
It does not mean you need to learn complicated technical language or memorise special commands.
For a PM or BA, it is much more practical.
You are learning how to explain your task clearly, provide the right information and guide the AI towards the type of output you need.
Why Does Prompting matter?
Imagine asking: “Create some user stories.”
The AI has very little information to work with.
Now imagine telling it what product you are working on, who the user is, what problem you are solving, what requirements you already know and how you want the user stories structured.
The second prompt gives the AI much more to work with.
This is why the same AI can produce very different results depending on the prompt and context you provide.
Where Can PMs & BAs use prompting?
Prompting can support many everyday product and business analysis activities.
You could use AI to help you:
- analyse customer research
- explore product problems
- draft requirements
- create or improve user stories
- develop acceptance criteria
- analyse business processes
- brainstorm solutions
- summarise documents
- prepare stakeholder communication
- explore risks, assumptions and dependencies
- challenge your thinking
The goal is not to hand your job over to AI. The goal is to use AI to help you think, analyse, create and work faster.
What Makes a Good Prompt?
A useful prompt usually helps the AI understand four things:
Task: What do you want it to do?
Context: What does it need to know?
Expectations: What should it consider or avoid?
Output: What should the result look like?
You will learn how to put these elements together in the next topic, How to Write Effective Prompts.
Prompting is a conversation
You do not need to create the perfect prompt on your first attempt.
Start with what you know. Look at the response. Add missing information. Correct assumptions. Ask questions. Change the direction if needed.
This is often a much better way to work with AI than trying to put everything into one enormous prompt.
DSM Tip
Good prompting is not about finding magic words.
It is about helping the AI understand your task, context and expectations, then working with the response until you get something genuinely useful.
