How to Explain IETF RFC Errata from Pasted RFC Text
Errata explainers invent ID 8123 and Verified. The paste had 200 vs 201. Ask which status the source intends.
The matching generator is the IETF RFC Errata Explainer from Pasted RFC Text (No Invented Errata IDs) (Ietf Rfc Errata Explainer From Pasted Rfc Text No Invented Errata Ids) 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).
Quote the conflicting fragments first
Explain possible errata in pasted RFC text. No invented errata IDs, RFC numbers, or official verdicts. 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:
Pasted RFC text (quote-only): [Text]
RFC number I lock (or UNKNOWN): [RFC]
Errata type labels I allow: [Types or editorial technical]
Words I must not use: [Banned]
What I must never invent (errata IDs, verdicts, extra RFCs): [Never]
Output format: [Format]
Language: [Lang]
Max findings: [Max]
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.
Keep RFC UNKNOWN if the number was not locked
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: Text nouns, RFC, Types, Lang, Max. Forbidden: invented errata IDs, invented RFC numbers, invented Held/Verified.
- Quote map: each finding quotes a fragment from Text. If no conflict is in Text, write NO CONFLICT IN PASTE.
- Findings: at most Max items. Type only from Types. Suggested repair stays a question, not an official erratum.
- RFC handling: quote RFC or write RFC UNKNOWN. Do not invent RFC 9110.
- Refuse list: rfc-editor.org IDs, IESG Verified, W3C errata, 2119 MUST rewrites that add rules.
- Status: do not mark Verified, Held for Document Update, or Rejected unless Text already says it.
- Never: do not invent Errata ID 8123.
- Compliance pass: quote Banned and Never hits. Cut them. Count findings vs Max. 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.
Do not mark IESG Verified
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:
- Errata explainer from Text. Not a 2119 rewrite and not a W3C explainer.
- Never invent errata IDs, RFC numbers, or official verdicts.
- Stay at or under Max findings.
- 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 rfc-editor IDs and 2119 rewrites
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 (ietf rfc errata explainer, no invented errata ids, pasted rfc text only) 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.