Audit your job week before the AI touches a bid
Lesson 1 of 5 · The job week
By the end you can turn one real week of bids, calls and paperwork into a table that says what an assistant drafts, what it checks, and what stays with you.
1 · Learn the move · Template pattern
Most contractors hear about AI from a sales guy and start with the flashy thing: a chatbot on the website, a video of the crew. Start with your own week instead. Write down what you did, how long it took, and whether it comes back every week. Then sort each line. DRAFT: the model writes a first pass from facts you give it (the client update text, the proposal cover letter, the sub reminder). CHECK: it tests something against a record you give it (the invoice against the quote, the submittal log against the spec list, the change order against the original scope). YOURS: the price, the schedule promise, anything about whether the work meets code, anything that goes in a contract with your license number on it. That third column is not the tool being weak. It is the line that keeps your license. The best first job comes back 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, schedule promises, code questions and anything that goes in a contract 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 night, truck in the driveway. This week you wrote two bids, chased three subs for schedules, answered nine client texts about the same kitchen, sorted a pile of receipts for the bookkeeper, and spent Wednesday evening retyping a takeoff into a proposal. Your nephew says AI could do half of it. You have no idea which half.
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.