Cost the scripted run before the document review
Lesson 3 of 5 · The attorney's week
1 · Learn the move · Constraints + negative instructions
Having a model summarize one deposition is free, near enough. Summarizing every transcript in a matter, or indexing a forty-thousand-document production, is a line in the matter's budget, and under the ABA opinion the question of who pays for it is answered in the engagement letter and the bill, not assumed [P]. So before the first full run, do the arithmetic on paper: what one run uses, times the number of runs, times the price. The price is the one number the model must never supply. Prices change, and a model will state an old one with full confidence. Copy it from the provider's pricing page, write down the date you read it, and hand it over as an input. Then ask for the arithmetic line by line, a monthly figure, and a cap at which the script stops and asks. Two constraints that are this door's: the run does not start until the de-identification and consent steps are in the file, and the cost line never turns into a line about hours saved, because time actually expended is what the bill carries.
I am costing a scripted run that drafts [the task] from inputs that have passed the de-identification and consent steps. Inputs I will give you: tokens per run from my test [paste], the provider's price per token from its pricing page, copied today with the date [paste], the number of runs for the matter at my real volume [paste]. Constraints: never supply a price, a token count or a volume I did not give you; a missing input is a missing line marked [CHECK THE RECORD]; show the arithmetic line by line; give the matter figure and a cap at which the script stops and asks; say nothing about hours saved or fees. Add one line on what happens to the estimate if an input has not passed the consent step: the run does not start.
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.
- Claude. Claude Team, Enterprise and API inputs and outputs are not used for training by default; a BAA is available only on Enterprise and the first-party API after admin action. Researched Oct 6, 2026, not yet confirmed by a person, recheck by Dec 15, 2026.
- Claude. Claude Free, Pro and Max inputs can be used for training if the user allows model improvement, with retention up to five years if allowed and 30-day deletion otherwise (pages dated 2026-03-16 and 2026-07-01). Researched Oct 6, 2026, not yet confirmed by a person, recheck by Dec 15, 2026.
- OpenAI. OpenAI API inputs are not used for training by default; abuse-monitoring logs are kept up to 30 days; zero data retention is available by approval. Researched Oct 6, 2026, not yet confirmed by a person, recheck by Dec 15, 2026.
- OpenAI. OpenAI Business, Enterprise and Edu no-training defaults are reported by secondary sources only; the vendor trust pages returned 403 on the check date. Read the vendor page yourself. Researched Oct 6, 2026, not yet confirmed by a person, recheck by Dec 15, 2026.
- Microsoft. Microsoft Copilot and Copilot Chat with Enterprise Data Protection: prompts and responses are not used to train foundation models, the DPA applies, and Microsoft acts as processor (Learn page updated 2026-08-18). Researched Oct 6, 2026, not yet confirmed by a person, recheck by Dec 15, 2026.
- Google. Gemini in Google Workspace content is not human-reviewed or used for training outside the customer's domain; default retention is 18 months. Researched Oct 6, 2026, not yet confirmed by a person, recheck by Dec 15, 2026.
- Every vendor. Every vendor's no-training or no-retention term is a contract term, not the duty: it does not by itself satisfy Rule 1.6 or Formal Opinion 512: the duty to understand the tool, and for some uses to obtain the client's informed consent, sits with the lawyer and not in the terms. Researched Oct 6, 2026, not yet confirmed by a person, recheck by Dec 15, 2026.
2 · Your turn. You write the prompt
Marchetti & Ostrow wants a script that drafts a first-pass summary of every deposition transcript in a product-liability matter: sixty-one transcripts, averaging two hundred pages. The client's general counsel has asked for the cost before approving the use. The partner wants the figure, with the arithmetic, before anyone writes a line of code.
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.