Better results from AI rarely need clever tricks. Five habits that help any business owner get useful drafts, summaries and answers the first time.
Most disappointing AI answers come from short questions. “Write a welcome email” gets you something generic. The fix isn’t a secret formula. It is giving the AI what you would give a new staff member on their first day.
1. Say who it is for
Name the reader and what they care about. “A parent registering their 9-year-old for fall soccer, who wants to know dates, cost and what to bring” is far more useful than “a customer”.
2. Give it your real material
Paste the actual policy, menu, price list or previous email. AI is much better at working from your information than inventing it. If it doesn’t have the facts, it may fill the gap with something plausible and wrong.
3. Describe what good looks like
Length, tone and format. “Under 120 words, warm but brief, with the three dates as a list and one clear button at the end.” If you have an example you like, include it.
4. Ask it to check itself
Ask it to list anything it was unsure about, or anything it assumed. For a summary of a long document, ask it to quote the passage behind each point so you can verify it.
5. Iterate like you would with a person
The first draft is a starting point. “Shorter.” “Less formal.” “Move the price to the top.” Two or three rounds usually gets you there.
Write the request you would give a capable new hire, and you’ll get the answer a capable new hire would give.
A before and after
Before: “Write a reminder for appointments.”
After: “Write a text message reminder for a massage clinic. It goes out the day before. Include the client’s first name, time and therapist, ask them to reply C to confirm or R to reschedule, and mention our 24-hour cancellation policy in one short sentence. Keep it under 300 characters and friendly.”
One rule about private information
Don’t paste client names, health details, ID numbers or financial records into a general AI tool unless your organization has approved that tool for that kind of data. Replace them with placeholders when you are drafting.
From the DYOL blog. Photo by pparnxoxo on Unsplash.
Keep reading
All posts
What’s new in AI this autumn, in plain language
Cheaper fast models, agents that run on a schedule and new rules on labelling AI. A short tour of what changed and what it means for a small team.

AI agents on a schedule: what it means for a small team
Agents can now wake up at 7 a.m., check something and report back. What that looks like in a café, a clinic or a club, and where to be careful.

AI agents, in plain English
Everyone is talking about agents. What the word actually means, what an agent can safely do for a small business today, and what it can’t.
A free 20-minute conversation, then an honest assessment. You’ll know what it costs and how long it takes, in writing, at a fixed price.
Or email lloyd.delacruz@outlook.com. We reply within 24 hours.
