Smarter by Thursday logo

Smarter by Thursday

Archives
Log in
Subscribe
August 11, 2026

Issue 32: Smarter by Thursday

Smarter by Thursday — Issue 32

Issue 32 · week of August 10, 2026

Smarter by Thursday

One practical AI win, every week. No jargon required.

By Dr. Rowan Hayes · Estimated read time: 6 minutes

If you are between 40 and 70, AI is no longer a curiosity sitting on the edge of your life. It is already shaping how people research expensive purchases and how they handle awkward professional messages they would rather not write themselves. Both topics matter because they save time, but they also expose a new risk: if you ask badly, AI will confidently give you something that sounds useful and is not actually useful.

Try at least one before Sunday. That is the whole assignment.

Use Case 1 of 2

Use Case 1: researching a major purchase decision

On a Tuesday afternoon in late August, Linda, 58, is sitting at her kitchen table with a legal pad, a mug of tea, and a headache she did not ask for. Her old car needs replacing, and she has already spent two evenings reading reviews that seem to contradict one another. One site says the model is “remarkably reliable.” Another says the infotainment system is a nightmare. A neighbor swears by a different brand. Linda does not want a glamorous answer. She wants a sane one: what fits her budget, what is likely to last, and what questions will help her avoid being sold something she will regret in a year.

This matters because major purchases are not just about price. They affect your monthly budget, your time, your comfort, and your peace of mind. Recent research and industry reporting suggest that buyers increasingly use AI to narrow options, compare trade-offs, and validate decisions before talking to a salesperson, but they still want human judgment at the end of the process. In other words, AI is useful when it acts like a thoughtful research assistant, not a replacement for common sense.

Here is the exact prompt to use:

Copy and paste this into ChatGPT or Claude:

You are my personal buying advisor. I am considering a major purchase and I want a clear, practical overview, not hype.

Before you recommend anything, ask me up to 10 focused questions so you understand my situation. Cover: - my budget range, including what a stretch budget would be - my location - how I plan to use this item - my priorities, such as reliability, safety, long-term cost, ease of use, resale value, or appearance - any constraints, such as no used items, must be available within 30 days, need financing, or physical limitations

After I answer, do all of the following: 1. Summarize my needs in 5 bullet points in plain language. 2. Based on public information up to your knowledge cutoff, outline 3 to 5 good options for me. 3. For each option, include the model or name, the typical price range, the main pros and cons for my situation, and any known reliability or quality issues. 4. Explain the trade-offs I am making if I choose cheaper, mid-range, or premium options. 5. Give me 8 to 10 specific questions I should ask a salesperson, contractor, or installer so I do not get taken advantage of. 6. Suggest a simple next-step plan I can follow over the next 7 days without feeling overwhelmed.

Begin by asking your questions and wait for my answers.

Why this prompt works: It works because it forces the AI to slow down before it starts talking. The first step is not advice; it is clarification. That matters, because a good purchase decision depends on specifics like location, usage, and budget, and AI shopping behavior research shows buyers use these tools most effectively when they help narrow choices and compare options rather than decide for you. The prompt also asks for plain language and trade-offs, which is exactly what most people need.

One thing to watch out for AI can sound more certain than it should. It may miss local pricing, current promotions, recent recalls, or the newest reliability problems if those happened after its knowledge cutoff. Treat its answer as a strong first draft, then verify the final shortlist with current local sources, dealer quotes, and reviews from real owners.

Use Case 2 of 2

Use Case 2: writing a professional decline email

On a Thursday morning at 9:10, Marcus, 64, opens his inbox and sees a request from a former colleague asking him to join a committee, review a proposal, and “hop on a quick call next week.” Marcus likes this person. He also knows that “quick call” often means an hour of his life. He does not want to sound cold. He does not want to over-explain. He definitely does not want to write a reply that becomes a long apology disguised as an email.

This matters because decline emails are where many capable people lose time and clarity. They either say yes when they mean no, or they write a message so padded with excuses that it invites more negotiation. A good AI prompt can help you keep the message short, respectful, and firm. That is useful in professional settings where people want clarity more than performance.

Here is the exact prompt to use:

Copy and paste this into ChatGPT or Claude:

You are helping me write a professional decline email.

The situation is: [paste the request or describe it briefly]. The person is: [boss / colleague / client / vendor / acquaintance]. My relationship with them is: [close / cordial / formal]. My goal is to politely decline without overexplaining, sounding defensive, or leaving room for confusion. Tone I want: warm, respectful, and firm.

Write 3 versions: 1. Very concise and professional 2. Warmer and more personal 3. Slightly more diplomatic if the request is sensitive

For each version, make sure it: - says no clearly - avoids long excuses - does not sound defensive - does not promise future help unless I choose to include that

Then, after the 3 versions, give me: - one sentence I should avoid because it sounds too apologetic - one sentence I should avoid because it sounds too vague - one optional closing line if I want to keep the relationship cordial

Why this prompt works: It works because it defines the job precisely. AI writes better when you tell it the relationship, the tone, and the exact boundaries of the message. It also asks for multiple versions, which is useful because the right decline for a client is not the same as the right decline for a friend. That structure helps the model produce cleaner language instead of defaulting to generic politeness.

One thing to watch out for AI can make a refusal sound polished but slippery. If you are too vague, the recipient may read it as “maybe later.” If you are too soft, the email can become an invitation to keep asking. Use the draft, but make sure the final sentence actually closes the door if that is what you intend.

Know someone who spends too long on things AI could do in two minutes? Forward this to three people who subscribe and I will send you my free AI Prompt Starter Pack: 20 ready-to-use prompts for everyday life.

Next Thursday how to use AI to organize medical paperwork and write a difficult family message

By Dr. Rowan Hayes


Know someone who spends too long on things AI could do in two minutes?

Forward Smarter by Thursday to three people who subscribe and I will send you my free AI Prompt Starter Pack: 20 ready-to-use prompts for everyday life.

Forward by email Open in browser Share on Facebook
Smarter by Thursday · By Dr. Rowan Hayes · drrowanhayes.com
Unsubscribe · View in browser

Don't miss what's next. Subscribe to Smarter by Thursday:
← Newer Issue 32: Smarter by Thursday Older → Issue 32: Smarter by Thursday
Bluesky
Powered by Buttondown, the easiest way to start and grow your newsletter.