How to Write Series 7 Items with Rationales (Not Advice)
Series 7 drills collapse into advice when a stem tells the reader to buy the bond. They also collapse into dumps when someone pastes a recalled item. You want original items, user-supplied numbers, and a banner that this is not a FINRA exam.
The matching generator is the Series 7 Item Writer with Rationales (Not 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).
Put the not-advice banner first
Write original Series 7-style items with rationales from public topic headings you paste. Not investment advice. No exam dumps. 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:
Public outline headings I pasted (not a dump): [Outline]
How many items: [Count]
Item style (stem plus 4 options): [Style]
Formulas or tables I allow you to use: [Tables]
Facts that must appear in a stem: [Facts]
Topics to avoid: [Avoid]
Learner level: [Level]
Words I must not use: [Banned]
Disclaimer line I want: [Disclaimer]
Timebox per item in minutes: [Time]
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.
Map items to pasted outline headings only
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 investment, tax, or legal advice. Practice items only. Not a FINRA exam.
- Map each item to a pasted Outline heading. If a heading is missing, do not invent a FINRA task ID.
- Write Count original items. Stem uses only Facts and Tables. Four options, one key, rationale, distractor autopsy.
- Calculations: show arithmetic from Tables. If a number is not in Tables or Facts, write NOT IN INPUTS.
- Avoid list: skip Avoid topics.
- Debrief: what the learner should look up in their own outline. No pass-score claim.
- Refuse: dumps, recalled items, personal portfolio advice.
- Compliance pass: quote Banned words and advice-shaped sentences. 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.
Show the arithmetic from tables you were given
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:
- FINRA Series 7 topical practice. Not Series 63, 65, 66, or SIE unless Outline says so.
- Never give a buy/sell recommendation.
- Never reproduce a live exam question.
- Do not invent a passing score or exam fee.
- Disclaimer must appear at the top of the output.
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.
Refuse buy/sell language and pass-score claims
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 (series 7 item writer, finra series 7 rationales, series 7 not 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.