How to Write an RFC Comment Disposition Log from a Review Thread
Disposition logs fail when they invent unanimous consensus. Three comments is not a vote. The chair was unnamed.
The matching generator is the RFC Comment Disposition Log from a Review Thread (No Invented Consensus) (Rfc Comment Disposition Log From A Review Thread No Invented Consensus) 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).
Index every commenter before you code a row
Turn a pasted RFC review thread into a disposition log. No invented consensus, owners, or decisions. 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:
RFC id and title: [RFC]
Pasted comment thread (author, quote, timestamp if present): [Thread]
Disposition codes I allow: [Codes]
Chair or editor I may name (or NONE): [Editor]
Decisions already recorded outside the thread (or NONE): [Record]
Next meeting or freeze date I can prove (or NONE): [Next]
What I must never claim: [Never]
Words I must not use: [Banned]
Word budget for the summary: [Budget or 200]
Output format (markdown table vs numbered list): [Format]
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.
Use only the disposition codes you listed
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: RFC id, every commenter in Thread, every code in Codes, Editor, Record, Next. Forbidden: voters and rulings not in Thread or Record.
- Comment index: one row per distinct comment in Thread. Quote a short excerpt. Do not merge two authors into one voice.
- Disposition table: comment id, author, code from Codes only. If the thread does not state a decision, mark needs-author or deferred, never accepted.
- Consensus line: only if Record or a quoted majority in Thread supports it. Else write no consensus recorded.
- Open questions: items with no disposition. Do not assign an owner unless that person posted in Thread.
- Next step: only Next. If NONE, write freeze date not specified.
- Summary under Budget words. Format as Format.
- Compliance pass: quote Banned words, invented votes, invented chair rulings. Cut them. Print word count vs Budget.
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.
No consensus line without a recorded decision
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:
- Disposition log from a pasted thread. Not a new RFC and not meeting minutes.
- Never invent consensus, a vote count, or an owner who did not comment.
- Use only disposition codes in Codes.
- If Next is NONE, do not pick a freeze date.
- 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.
Leave freeze dates blank when Next is NONE
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 (rfc comment disposition log, rfc review thread tracker, no invented consensus) 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.