How to Draft a Mutual NDA Intake Questionnaire (Not Legal Advice)
NDA intake goes wrong when a chatbot drafts Delaware law and a 5-year term that were not in the paper. You wanted questions both sides can answer. Not a contract. Not a DPA.
The matching generator is the Mutual NDA Intake Questionnaire from Pasted Policies (Not Legal Advice) 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 a draft NDA
Turn pasted NDA policies into an intake questionnaire for a mutual NDA. Not legal advice. No invented jurisdictions or terms. 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:
Parties I may name (or roles only): [Parties]
Pasted policy excerpts (definition of confidential info, term, venue, residuals): [Policies]
Purpose of the talk I can prove: [Purpose]
Data classes I already know will be shared: [Data]
What I must not promise: [Never]
Questions my counsel already requires: [CounselQs or NONE]
Words I must not use: [Banned]
Max questions: [Count or 12]
Whether this must stay mutual (both sides): [Mutual]
Not-advice banner language I want: [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.
Ask business facts, not legal conclusions
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:
- Banner: not legal advice, not a draft NDA, not a DPA. Quote Banner or a one-line default.
- Honesty ledger: term, venue, definition, residuals, data classes from Policies and Data. Forbidden: jurisdictions and years not pasted.
- Questionnaire: up to Count numbered questions. Each must be answerable from a business fact, not a legal conclusion.
- Mutual check: if Mutual is yes, every question has a both-sides version. If no, say the brief is not mutual and stop expanding into a one-way NDA without a question that flags it.
- Gaps vs Policies: terms in Policies that have no question yet.
- Never list: quote Never. Do not turn them into promises in the questions.
- CounselQs: include only those. If NONE, do not invent bar-exam questions.
- Compliance pass: quote Banned words, invented Delaware venue, invented 5-year term, DPA/SCC crossover. Cut them.
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.
Keep every question mutual if the brief is mutual
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:
- Intake questionnaire only. Do not draft NDA clauses.
- Not legal advice. Not a DPA or SCC.
- Never invent a governing law, term of years, or residuals clause.
- Keep it mutual if Mutual is yes.
- 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.
Do not invent venue, term, or residuals
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 (mutual nda intake questionnaire, nda policy checklist, not legal advice) 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.