How to Talk to AI
Five practical techniques that turn vague AI output into something you can actually use.
The way you phrase your instructions to AI is called prompting, and it matters more than most people realise. The quality of the output is entirely dependent on the quality of the input. This is not a slight difference. It is the difference between getting back something generic and useless versus something that saves you real time. Let me show you exactly what I mean.
The Lazy Prompt vs The Crafted Prompt
Here is the same task, done two ways.
The lazy prompt:
You will get back a generic list of popular destinations with vague suggestions. It will read like a travel brochure written by someone who has never met you. Useless.
The crafted prompt:
We are based in Sydney and would fly from there. Budget is around $8,000 AUD total including flights, accommodation, and food, but not shopping.
We are not interested in group tours or tourist-heavy experiences. We prefer walking, local food, and quieter neighbourhoods over temples and shrines (though we will visit a couple). We have been to Tokyo before for three days, so we do not need a basic Tokyo intro.
We want to split the trip roughly: 3 nights Tokyo (exploring areas we missed last time -- Shimokitazawa, Yanaka, Koenji), 3 nights Kyoto, 2 nights somewhere rural or coastal that most tourists skip, 2 nights Osaka.
Important: One of us is vegetarian. Not vegan, but no meat or fish. I know this is hard in Japan. I need practical advice on this, not just "it will be fine."
What I need: A day-by-day outline (not hour-by-hour). For each location, suggest a specific neighbourhood to stay in and why, one or two must-do things, and at least one restaurant or food experience. Flag anything we need to book in advance.
Tone: Practical, like advice from a friend who has lived there, not a guidebook."
The second prompt gives the AI everything it needs: who you are, where you are coming from, what you have already done, your budget, your tastes, your constraints, and exactly what format you want the answer in. The output will be something you can actually use to book a trip, not something you need to throw away and start again.
That is the core lesson of prompting. The more context, specificity, and constraint you provide, the better the result. Every detail you include eliminates a decision the AI would otherwise make on its own -- usually badly.
The Anatomy of a Good Prompt
A well-crafted prompt typically includes some or all of these elements:
Role: Who should the AI be? "You are an experienced physiotherapist who works with people over 50 returning to exercise after a long break." This frames the vocabulary, the depth, and the perspective of the response.
Context: What is the situation? The more background you give, the more relevant the output. Do not assume the AI knows anything about your specific situation.
Task: What exactly do you want? "Write," "Analyse," "Compare," "Identify," "Draft," "Explain." Be precise about the action.
Constraints: What are the boundaries? Length, format, tone, audience, things to include, things to avoid. Constraints are where good prompts become great prompts.
Examples: If you want output in a specific style or format, show the AI an example. "Here is an email I wrote last week that I was happy with. Match this tone and style." This is one of the most powerful prompting techniques and the most underused.
Output format: Tell it exactly how you want the response structured. "Give me a table with four columns." "Structure your response as: first the diagnosis, then three options, then your recommendation with reasoning." "Use short paragraphs, no bullet points, no headings."
Example: Crafting a Difficult Message
Here is a prompt that demonstrates how much context changes the output:
Dad is 82, lives alone in a large four-bedroom house in the suburbs. Mum passed away two years ago. He is physically healthy for his age but has had two minor falls in the past six months, both at home. He is fiercely independent and has already shut down one conversation about this with my sister by saying "I am not going to a home."
I am not suggesting a nursing home. I want to raise the idea of downsizing to a smaller place -- a two-bedroom villa or apartment in the same area, close to his friends and his GP. Something easier to manage, single level, no garden maintenance.
The problem: If I come on too strong, he will shut down. If I am too vague, he will not take it seriously. I need to find the middle ground.
Help me draft a message (I will send it by email -- he reads email every morning) that:
1. Opens with something warm and specific, not a generic "how are you." Reference something real, like asking about his golf or his neighbour's dog.
2. Raises the topic gently but honestly. Acknowledge that I know he does not want to move to a home -- and that is not what I am suggesting.
3. Frames downsizing as gaining something (less hassle, more freedom, money freed up) rather than losing something.
4. Does not pressure him to decide anything. Just opens the door to a conversation.
5. Ends in a way that makes it easy for him to respond without feeling cornered.
Tone: Loving but direct. I am his son, not his case worker. Short sentences. No clinical language. No "I am concerned about your wellbeing" -- he would hate that."
That prompt gives the AI a specific person, a specific situation, a history of prior attempts, your emotional state (love, respect, worry), exactly what outputs you need, anticipated resistance, and clear guidance on tone. The response will be something you could actually send. Compare this to "Help me talk to my dad about moving" and you can see why prompting quality matters.
Example: Making Sense of Paperwork
When you upload a document to AI, do not just say "summarise this." Tell it what you need and why:
I need you to:
1. Compare the key coverage amounts to what a typical policy covers for a three-bedroom house in suburban Brisbane. Am I over-insured or under-insured on any category?
2. Identify any new exclusions or changes from what looks like a standard policy. Flag anything I should specifically ask them about.
3. Tell me what the excess structure is and whether it seems reasonable.
4. Give me a plain-English explanation of the flood and storm surge clause. I live 400 metres from a creek and this matters.
5. List the three most important questions I should ask when I ring them to negotiate, in order of importance.
Be direct. If this looks like a bad deal, say so. I would rather switch insurers than overpay out of laziness."
This prompt turns AI from a summariser into a practical advisor. You have told it your situation, what you need to decide, how to structure the analysis, and that you want honest answers rather than hedge-everything waffle. The output will be something you can use on the phone with your insurer, not a generic explanation of how insurance works.
Example: Creating Content With Your Voice
One of the hardest things for AI is matching a specific writing voice. The solution is to give it a sample and be explicit about what makes that voice distinctive:
[paste 500-1000 words of your own writing]
Before you write the post, tell me what you observe about my writing style: sentence length, tone, use of humour, level of formality, how I handle recipes versus storytelling, and any distinctive patterns. I want to verify that you have understood my voice before you attempt to replicate it.
Once I confirm, write a 600-word post about the lost art of the weeknight roast -- how our parents did it without thinking and we have somehow convinced ourselves it is too hard. The post should follow the same structure as my sample: open with a specific personal moment, explain why the conventional wisdom is wrong, describe a simpler approach, and close with something warm and slightly funny."
The key technique here is asking the AI to describe your voice back to you before it writes. This forces it to explicitly identify the patterns rather than making vague approximations. If its description does not match what you think your voice is, correct it before it writes. This two-step process (analyse then write) produces dramatically better results than "write something in my style."
Iteration: The Real Skill
Your first prompt rarely produces a perfect result. That is normal. The real skill is in the follow-up. Good iterative prompts are specific about what is wrong and what you want changed:
"The second paragraph is too vague. Replace the general claim with a specific example. Reference a real product, a real place, or a real situation."
"The tone is too formal. Rewrite the whole piece as if you are explaining this to a friend over coffee, not writing a Wikipedia article."
"This is too long. Cut it to 400 words. Keep paragraphs 2 and 5 intact. Condense everything else."
"You have given me a balanced analysis. I asked for a recommendation. Pick a side and defend it."
"The structure is right but the opening is weak. Give me three alternative opening sentences that start with a specific personal detail or a surprising fact, not a general observation."
Three to five rounds of focused iteration typically produces something excellent. The people who get disappointing results from AI are almost always the ones who accept the first output or give vague feedback like "make it better." Be as specific in your feedback as you were in your original prompt.
We have very politely avoided the topic of work. Click here if you fancy finding out how this stuff plays out on the job. Maybe.
Everything above applies at work too, obviously. But business prompts come with an extra consideration: you are often sharing information that is sensitive, confidential, or both. Here are some examples of how the same prompting principles work in a professional context, with privacy warnings where they matter.
Example: Writing a Proposal
Remember the lazy prompt "plan me a holiday" from above? Here is the work equivalent:
Useless. Now here is the same task with context:
My company: Assure Advantage, a specialist bid assurance consultancy. We help organisations identify structural risks in large IT procurement before they commit to contracts.
The client: A mid-tier Australian government department about to go to market for a core systems replacement worth approximately $50-80 million over 5 years. They have had two failed IT procurements in the past decade.
What I am proposing: An independent structural risk assessment of their draft RFP and evaluation framework before they release it to market. This is a 4-6 week engagement.
What I need: A 2-page proposal (not longer) that opens with their problem (failed procurements and the cost of getting this one wrong), positions our approach as different from standard risk consulting (we assess the structural design of the deal, not just the risk register), outlines the scope and timeline, and states the investment.
Tone: Authoritative but not arrogant. Peer-to-peer, as if written by someone who has seen this problem many times and knows how to solve it. No consulting jargon. No buzzwords. Short sentences. Direct language.
Do not include: Executive summary headings, "about us" sections, or any boilerplate. Start with their problem, not with us."
Same principles. Context, constraints, tone, format. The output will be something you can actually send.
Example: Preparing for a Difficult Workplace Conversation
I am a senior project manager in an IT services company. I have a team member, let us call him James, who has been with the company for 8 years. He is technically excellent but increasingly difficult to work with. He pushes back on every process change, openly criticises decisions in team meetings, and has started being dismissive toward two junior team members who joined in the last 6 months.
I have had two informal conversations with him about the behaviour. Both times he acknowledged the issue but nothing changed. My manager has asked me to have a formal conversation and document it.
I genuinely respect James's technical ability and do not want to lose him. But the impact on the team is real and getting worse.
Help me prepare for this conversation. I need:
1. An opening statement that is direct but not aggressive. I want to be clear this is formal without making it feel like an ambush.
2. Three specific examples I should raise (suggest the kinds of examples based on the behaviours I described, since I will substitute my own real ones).
3. How to handle the most likely pushback: that he will say the junior staff are not good enough and that processes are bureaucratic.
4. A way to end the conversation that gives him a clear path forward rather than just a reprimand.
5. What to document after the meeting.
Context: We are in Australia. I need to be mindful of fair work obligations. The company has an HR team but I want to handle this at my level first if possible."
More Business Prompts (With Privacy Warnings)
Competitive analysis: "Research [competitor name] and summarise their service offerings, pricing model, and market positioning. I want to understand where they are strong and where there might be gaps we could exploit." This is safe because you are asking about publicly available information.
Document review: "Review this contract and highlight any clauses that are unusual, one-sided, or that I should negotiate." Privacy warning: You are uploading a potentially confidential document. See the privacy section before doing this with sensitive contracts.
Financial analysis: "Analyse this spreadsheet and identify the top 3 cost categories that have increased by more than 10% year-on-year. Suggest areas to investigate for cost reduction." Privacy warning: Financial data is sensitive. Use a paid tier (which offers stronger data protection) and never upload data with client names or personal information unless your privacy policy allows it.
Strategy brainstorming: "Act as a business strategy consultant. Our company provides [service] to [market]. Revenue has plateaued at [amount]. Give me 5 strategic options for growth, with pros and cons of each." This is generally safe as you are sharing business context, not personal data.