Know what the scripted run costs before the backlog
Lesson 3 of 5 · The job week
By the end you can work out what a script that reads every job photo or receipt will cost, from a price you copied and dated yourself, and write the cap the script obeys.
1 · Learn the move · Constraints + negative instructions
Having a model read one receipt and file it against a job is free, near enough. Having it read two years of receipts, and then every photo from every job site, is a bill. Before the backlog run, do the arithmetic on paper: what one file uses, times the number of files, times the price. The price is the one number the model must never supply. Prices change, and a model will give you last year's with full confidence. Copy it from the provider's pricing page, write the date you read it, and hand it over as an input. Then ask for the arithmetic line by line, a monthly figure at your real volume, and a cap: the count or spend where the script stops and asks. Missing input means [NEEDS: ...], not a guess. The dated vendor notes under this lesson are where prices live; the lesson states none.
Work out what this run costs. Price, copied from the provider's pricing page on [date]: [paste]. One file uses about [N] input and [M] output tokens (from a test call). Files in the backlog: [count]. New files per month: [count]. Show the arithmetic line by line. Never supply or adjust a price yourself; if any input is missing, write [NEEDS: ...]. Then write a stop rule I can paste into the script: the file count at which it stops and asks me.
Vendor notes, dated
Prices and plan names move. Each note says when it was looked up, whether a person has confirmed it, and the day it comes due. Past that day, treat it as a question.
- Claude. Claude Pro is $20 a month billed monthly, or $17 a month billed annually. Researched Oct 6, 2026, not yet confirmed by a person, recheck by Dec 15, 2026.
- ChatGPT. ChatGPT Plus is $20 a month. Researched Oct 6, 2026, not yet confirmed by a person, recheck by Dec 15, 2026.
- Google Gemini. Google Gemini's paid consumer plan is Google AI Pro at $19.99 a month; Google AI Ultra starts at $99.99 a month. Researched Oct 6, 2026, not yet confirmed by a person, recheck by Dec 15, 2026.
- Anthropic. Anthropic's consumer plans (Free, Pro, Max) may use chats to train models under a setting the user controls, with five-year retention when training is on and 30 days when it is off; Claude for Work, Education, Government and the API are excluded. [P] Researched Oct 6, 2026, not yet confirmed by a person, recheck by Dec 15, 2026.
- Anthropic. Anthropic's usage policy, effective 2025-09-15, requires a qualified human reviewer and disclosure of AI use for housing, legal and financial decisions. [P] Researched Oct 6, 2026, not yet confirmed by a person, recheck by Dec 15, 2026.
- OpenAI. OpenAI's consumer plans train on chats unless the Improve the model setting is turned off, and a Temporary Chat is not used for training; Enterprise, Business, Edu and API data are not used by default. [S] Researched Oct 6, 2026, not yet confirmed by a person, recheck by Dec 15, 2026.
- Google Gemini. Google Gemini Apps keeps activity 18 months by default, keeps human-reviewed chats up to three years, and tells users not to enter confidential information. [P] Researched Oct 6, 2026, not yet confirmed by a person, recheck by Dec 15, 2026.
- Microsoft Copilot. Microsoft Copilot on a personal account may use chats to train models unless the user opts out; Entra and Microsoft 365 work accounts are excluded. [S] Researched Oct 6, 2026, not yet confirmed by a person, recheck by Dec 15, 2026.
- Procore. Procore publishes no price; its pricing page says the quote depends on the products chosen and annual construction volume. Researched Oct 6, 2026, not yet confirmed by a person, recheck by Dec 15, 2026.
2 · Your turn. You write the prompt
Your office manager set up a script that reads each receipt photo and writes the job number, the vendor and the amount into the bookkeeping sheet. The test on ten receipts was clean. There are 1,900 receipts in the shoebox years and about 120 a month going forward, and she asked what the backlog costs before she lets it run overnight.
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.