Audit your week before you hand the first task over
Lesson 1 of 5 · Run your week
By the end you can turn one real week of listing, showing and follow-up work into a table that says what an assistant can draft, what it can check, and what stays with you.
1 · Learn the move · Template pattern
Agents pick their first AI job by what sounds impressive: a chatbot, a video, a market report. Pick it from your own calendar instead. Write down last week task by task, with rough hours, and whether it repeats. Then sort every line into three columns. DRAFT: the model can write a first version from facts you give it (the just-listed email, the open house follow-up text, the showing feedback summary). CHECK: it can test something against a record you give it (the MLS entry against the tax card, a listing description against the disclosure). YOURS: pricing advice, what you say to a seller about an offer, anything that describes who should live in a home, anything you would be fined for if it were wrong. The third column is not the tool failing. It is the line the rest of this door is built on. The best first job repeats every week, eats the most hours, and sits fully in the first two columns.
Here is my last week, task by task, with rough hours: [paste]. Sort it into a table: task | hours | repeats weekly? | DRAFT / CHECK / YOURS | one line why. Pricing opinions, offer strategy, and anything that describes the people a home suits go in YOURS. Then name the one repeating task with the most hours that is fully DRAFT or CHECK. If my notes do not say how long something took, write [NEEDS: hours].
2 · Your turn. You write the prompt
Friday, 4 pm. This week you held two open houses, wrote three listing descriptions, texted forty-one leads one at a time, pulled comps for a Tuesday appointment, chased a lender for a pre-approval letter, and spent most of Wednesday re-entering a listing after the photographer sent a new set. Everyone says AI will give you your evenings back. You have no idea which task to start with.
Write the prompt for this scenario as given, or swap in a real one from your own work. The score works the same either way.
Remember: the AI sees only your prompt, not this page. If the situation isn't in your prompt, it doesn't exist.
Optional. These shape the output when you run your prompt below, not your score.