How to Build a Parent-Child Qualitative Codebook
Codebooks invent quotes. Nested codes from the theme inventory only. QUOTE NOT IN INPUTS.
The matching generator is the Parent-Child Qualitative Codebook from a Theme Inventory (No Invented Quotes) 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).
Nest children only under pasted parents
Build a parent-child qualitative codebook from a pasted theme inventory. Never invent quotes, frequencies, or codes. 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:
Theme inventory (parent and child labels as pasted): [Themes]
Definition style I lock: [Style]
Words I must not use: [Banned]
What I must never invent: [Never]
Output format: [Format]
Language: [Lang]
Inclusion notes I allow (or NONE): [Include]
Banner I require: [Banner or Not a transcript analysis]
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.
Define codes with inventory words
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: Themes labels, Style, Include, Banner, Lang. Forbidden: invented quotes, invented %, extra codes.
- Banner line.
- Codebook table: parent, child, definition from Themes words only, inclusion from Include or NONE.
- Example quote column: QUOTE NOT IN INPUTS on every row (inventory has no quotes).
- Frequency: FREQ NOT IN INPUTS.
- Orphans: Themes labels that could not nest; do not drop them.
- Refuse: inventing participant IDs, inventing inter-rater kappa, inventing interview excerpts.
- Compliance pass: Banned and Never. 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.
Print QUOTE NOT IN INPUTS on every row
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:
- Parent-child codebook from Themes inventory only. Not a notes-to-themes job.
- Never invent quotes, frequencies, or extra codes.
- Keep Banner visible.
- 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 invented frequencies and kappas
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 (parent child qualitative codebook, theme inventory no invented quotes, codebook from themes not notes) 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.