Write A/B test hypotheses backed by your past results

About this exercise

You're planning next quarter's email tests at Harrow & Hale, a men's shoe brand. Write exactly 3 numbered hypotheses, each one sentence in the shape If we..., then... will rise, because... (citing a past result from the notes), under 30 words. Each tests only one change, none touches discounts, and reply with only the plain-text list.

Common mistakes when you ask AI for this

• No hypothesis shape. The AI writes vague test ideas without a prediction or reason. Try: Show it: "If we..., then... will rise, because..."
• Not grounding the reason. The AI makes up reasons from general email advice. Try: Add: "Each because cites a result from our test log."
• Testing what's off-limits. Discount tests and redesigns are in the notes, and the AI picks them up. Try: Add: "One change per test. No discounts, no redesign."
• Getting a planning doc. The AI writes a table with bold headers and success metrics. Try: Add: "Exactly 3 numbered sentences, plain text."

What a strong prompt includes

• Sets the hypothesis shape
• Cites past results
• One change each
• Rules out discounts
• Asks for only the list

Practice this now ↑

Related exercises

• Accept a job offer and confirm the exact terms (Writing AI · Job seekers)
• Announce a referral bonus with the steps to claim it (Marketing AI · HR and recruiting)
• Answer a 'where is my order' email with the real new date (Writing AI · Customer support teams)
• Answer a big discount ask with two priced options (Writing AI · Sales and customer success)
• Answer a buyer's HOA questions from the bylaws (Research AI · Real estate agents)