Audit your buying week before you hand the first task over
Lesson 1 of 5 · The buying week
1 · Learn the move · Template pattern
Land buyers pick a first AI job by what the forum is excited about this month: an auto-dialer, a letter machine. Pick it from your own week instead. Write down what you did, how long it took, and whether it repeats. Then sort every line. DRAFT: the model writes a first version from records you pasted (the owner letter from a verified name and parcel, the weekly pipeline note, the summary of a title search you ordered). CHECK: it tests one thing against a record you pasted (the list against the scrub file, the acreage in your letter against the deed, the parcel numbers against the plat map). YOURS: what the land is worth, any statutory date, any call or text to an owner, anything you tell an heir about their share. The third column is not the tool's limit. It is the line that keeps you out of a complaint. The best first job repeats every week, eats the most hours, and sits entirely in DRAFT or CHECK.
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. Value opinions, statutory dates, any contact with an owner and anything said to an heir 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 evening. This week you pulled a county list of 1,400 tax delinquent parcels, scrubbed it against the no-contact file by hand, wrote sixty owner letters one at a time, drove to look at three tracts, called a clerk about a redemption period, and spent Thursday retyping a plat map's parcel numbers into your sheet. A forum post says AI could do all of it by Tuesday. You would settle for one task.
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.