How to Write FRM Part I Items with Rationales
FRM items fail when they dump a remembered stem and a VaR dollar figure. Tag the reading. Keep Numbers NONE if you have none.
The matching generator is the FRM Part I Item Writer with Stem, Three Distractors, and Reading Tag (No Exam Dump) (Frm Part I Item Writer Stem Three Distractors Reading Tag No Exam Dump) 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 an exam dump
Write original FRM Part I items with a stem, three distractors, one key, and a reading tag. Not an exam dump and not CFA. 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:
Reading tag I allow (as pasted by the learner): [Reading]
Topic nouns I may use: [Topics]
Formula names I may use (or NONE): [Formulas]
Number of items: [Count or 2]
Words I must not use: [Banned]
What I must never invent: [Never]
Output format: [Format]
Language: [Lang]
What this is not: [Not]
Numbers I may use (or NONE): [Numbers]
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.
Stem plus one key and three distractors
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 an exam dump, not CFA, not GARP advice. Quote Not. Original teaching items only.
- Honesty ledger: Reading, Topics, Formulas, Numbers, Count, Lang. Forbidden: remembered GARP stems, item IDs, passing-score claims.
- Items: exactly Count. Each has stem, A/B/C/D with one key and three distractors, key letter, rationale tied to Reading, reading tag quoted.
- Numbers: only Numbers. If NONE, write qualitative stems. Do not invent a VaR dollar figure.
- Distractors: plausible mistakes from Topics, not jokes. Label why each distractor is wrong using Topics only.
- Refuse: dumped items, CFA ethics stems, 'actual exam question'.
- Never: do not paste a remembered FRM item. Do not invent a GARP reading code if Reading is a plain tag.
- Compliance pass: quote Banned and Never hits. Cut them. 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.
Tag the pasted reading on every item
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:
- FRM Part I original items from Reading. Not CFA and not an exam dump.
- Stem, one key, three distractors, reading tag.
- Only Topics, Formulas, and Numbers named in Inputs.
- Not certification advice.
- 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.
Refuse CFA stems and GARP item IDs
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 (frm part i item writer, frm stem distractors reading tag, no frm exam dump) 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.