Why we all need to become skilled AI questioners

AI prompt engineering involves creating clear, specific, goal-oriented questions to get the most useful responses from AI systems.

This is nothing new, it’s just good management. In the army, if someone doesn’t complete a task as expected, the fault lies with the person who gave the instructions. If you ask someone to ‘research the leading brands of vegan burgers’, but what you really meant was ‘find the brands of vegan burgers operating in food service, decide if any might be suitable for school meals, get specifications and prices’, then the miscommunication is on you.

AI as a research assistant

Encouraging your team to use AI for research can significantly boost productivity.

The quality of AI-generated research is a direct result of how clear and specific prompts are. This is especially helpful when you’re unsure of what you want, or if there is a lack of clarity from a manager or other input.

For example, if you ask someone to research vegan burgers without providing details, the team member might ask the AI: ‘My manager has asked me to research vegan burgers but hasn’t given me any details. I want to do some initial research and then check back with them. How should I start my research, and what should I consider? What’s the best way to present the initial results so they think I’m doing a good job? I only want to spend two hours on this before checking in with them’.

When you input this into an AI like ChatGPT or Perplexity, the response might not be exactly what you expected. Remember, King Midas didn’t really want everything he touched to turn to gold, but unfortunately didn’t get a chance to refine his question. Spending 30 minutes redefining the prompt almost always yields better results and improves your skill for next time.

There are countless advantages when using AI in research. For example, AI can conduct comprehensive literature reviews by analysing and summarising findings from numerous sources, this helps researchers to quickly grasp the current state of knowledge in a given field.

AI research assistants can also rapidly sift through vast amounts of data, including scientific papers, databases and other sources, to collect relevant information much faster than humans. They analyse data as it's being collected, identifying patterns and trends instantly.

AI as a business coach

I spend much of my day using various AIs not only to assist with tasks but to also suggest what I should do. It’s like having the best professional coach around. You could start with a prompt like, ‘How can I improve my management skills?’ and then refine it to ‘How would Richard Branson advise me to improve my management skills?’ or ‘What advice from 'Like a Virgin: Secrets They Won't Teach You at Business School' can help me improve my management skills during team meetings?’.

For the bigger questions like, ‘How do I know if my career is going well and if I am happy?’, you could try having a chat with Chat GPT 4o. The app now has a conversation mode, meaning it’s able to audibly converse with you on any topic you like and never get bored talking about you. It feels like a real conversation, it can go on as long as you like, and you can always ask for a summary by saying, ‘Give me a summary of what we’ve been talking about’.

AI is increasingly being utilised as a business coaching tool. It can analyse vast amounts of data to offer tailored advice based on a specific business challenge and they can provide objective insights without fear of judgement.

AI models can also recognise patterns and potential solutions in information shared by users, offering deep-level insights, as well as from real-life coaches. Some are even specially trained to focus on different subjects. For example, Jodie AI specialises in lifestyle design, productivity and starting a business.

The future of management

As AI systems become more integrated into business operations, managers will need to adapt their skills and approaches to effectively leverage these technologies. Managers who can skilfully engineer prompts to optimise AI performance can gain a significant advantage over those who cannot effectively leverage AI tools.

Being a good prompt engineer requires a unique combination of technical knowledge and soft skills, making it a challenging yet increasingly important activity in this rapidly evolving field.

There is a theory that the future of modern management will be almost entirely about prompt engineering. The office would be staffed by super responsive AIs who are just hanging around to do whatever you would like them to do.

The huge challenge will be you knowing what you want and translating that into questions that they can understand. If you cannot successfully communicate your points to AI, it may not be able to help you. However, for those who do master this skill, they could see increased levels of productivity and efficiency, with once time-consuming tasks whittled down considerably.

AI won’t be limited to business activity, it will be everywhere, and the need for good prompts will become a ubiquitous part of our daily experience. So we might as well become good prompt engineers!

The good news is that it’s quite easy to become a good prompt engineer; just start a conversation with an AI about anything you like and see where the journey takes you. Each step of the way, you will be automatically honing your prompt engineering skills and abilities.