How to Extract a Contract Clause Table from Pasted Text
Clause tables invent a statute and an enforceability call. Quote the paste. Mark ABSENT clauses ABSENT. Put the not-legal-advice banner first.
The matching generator is the Contract Clause Extract Table from Pasted Text (Not Legal Advice, No Invented Statutes) (Contract Clause Extract Table From Pasted Text Not Legal Advice No Invented Statutes) prompt. Browse related cards in the PromptDig library (Browse more prompts). When a filled run survives, share the version you actually use (Share a prompt).
Banner that this is not legal advice
Extract a clause table from pasted contract text. Quote-only cells. Not legal advice. No invented statutes or enforceability calls. Start by filling Inputs, not by asking the model to remember last week's run. If a field is blank, write NONE or NOT IN INPUTS and leave it blank through Generate. The card is built so the model cannot honestly invent a number, owner, URL, or command that you did not paste.
Paste these fields before you hit run:
Pasted contract text (quote-only source): [Text]
Clause IDs I allow (or UNKNOWN): [Clauses]
Columns I lock: [Columns]
Words I must not use: [Banned]
What I must never invent (statutes, enforceability, missing clauses): [Never]
Output format: [Format]
Language: [Lang]
Max rows: [Max]
Not-advice banner I require: [Banner]
That inventory is the honesty ledger. Anything that does not appear there is forbidden in the draft. If you catch yourself adding a nice-to-have after the run, you are no longer using the card. You are ghostwriting. Put the extra fact in Inputs and run again.
Quote each cell from the pasted text
Generate is numbered on purpose. Do not skip a step because the first paragraph looked done. The early steps exist to stop later prose from smuggling claims.
Walk the Generate list in order:
- Honesty ledger: Text nouns, Clauses, Columns, Lang, Max. Forbidden: invented statutes, invented enforceability, invented clauses.
- Banner: print Banner first. This is not legal advice and not a redline.
- Extract table: one row per allowed clause actually present in Text. Cells quote Text or write NOT IN INPUTS. At most Max rows.
- Provenance: each row maps to a clause ID or quote fragment in Text.
- Refuse list: statute cites, "this is unenforceable," redlines, signature-page invent, missing exhibits invent.
- Missing clauses: if Clauses names an ID absent from Text, write ABSENT rather than drafting it.
- Never: do not add a governing-law statute. Do not declare validity.
- Compliance pass: quote Banned and Never hits. Cut them. Count rows vs Max. Format as Format.
If a step asks for a version lock, quote the version from Inputs in the output. If a step asks for a refuse list, keep the refuse list in the published artifact, not in a sidebar you delete. Reviewers should see what the model was not allowed to do.
Refuse invented statutes and redlines
Most failures are the same shape: a missing field gets a confident fill. A conversion rate appears. A Gradle task appears. A flash point appears. A caption appears on a job that asked for slide text only. Your review is to search the draft for numbers, names, and commands, then grep Inputs. No match means cut.
Honor the constraints as hard stops, not vibes:
- Extract table from Text only. Not legal advice and not a plain-English explainer.
- Never invent statutes, enforceability, or missing clauses.
- Stay at or under Max rows.
- No emojis.
When the card says not legal advice, not certification, not an exam dump, or not a caption engine, that sentence belongs at the top of the output. Deleting it to look more finished is how you inherit risk.
Count rows against Max and list gaps
Finish with the compliance pass the prompt already asks for. Quote the banned-word hits. Cut them. Print character counts when the job has a cap. Print word counts when the job has a budget. List gaps as gaps. Five missing facts are more useful than one smooth paragraph.
Tags on the card (contract clause extract table, not legal advice extract, no invented statutes) are a reminder of the job shape, not an invitation to wander into a neighboring cluster. If you need a different surface, open a different PromptDig card rather than stretching this one.
Fill the card, then run
Replace every bracket. Run on ChatGPT, Claude, or Gemini. Read the ledger first, then the artifact. If the model invents a commit, KPI, DOI, PEL, bid, or logo, discard the run. Tighten Inputs. Run again. Share the filled card that survived, not the first draft that sounded done.