How to Sketch an ISO 27001 Statement of Applicability from a Control Inventory
SoA drafts invent Annex A rows. Applicability only from the inventory.
The matching generator is the ISO 27001 Statement of Applicability Sketch from Control Inventory (Not Certification Advice) (Iso 27001 Statement Of Applicability Sketch From Control Inventory Not Certification 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).
Map each inventory ID before you fill a cell
Sketch an ISO 27001 Statement of Applicability table from a pasted control inventory. Not certification advice; never invent control IDs. 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 control inventory (ID, title, in-scope flag, justification notes): [Inventory]
Standard edition I lock (or UNKNOWN): [Edition]
Applicable values I allow: [Flags or yes/no/partial]
Words I must not use: [Banned]
What I must never invent: [Never]
Output format: [Format]
Language: [Lang]
Max rows: [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.
Quote justification notes or write NOT IN INPUTS
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: inventory row count, Edition status, Flags, Lang, Max. Forbidden: invented control IDs, certification promises.
- Inventory map: each ID/title/flag present or NOT IN INPUTS.
- SoA sketch table: up to Max rows. Justification only from Inventory notes. Missing justification prints NOT IN INPUTS.
- Out-of-scope list: rows flagged no, with quoted notes only.
- Refuse list: invented A.5.x IDs, invented auditor names, invented certificate numbers.
- Diff notes: Banned/Never cuts.
- Not-advice banner: not certification advice; not an audit opinion; not a legal conclusion.
- Compliance pass: Banned/Never hits. Row count vs Max. Gaps list of five. 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.
Refuse invented certificate numbers
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:
- SoA sketch from Inventory only. Not certification advice and not a full ISMS.
- Never invent control IDs, certificates, or auditor findings.
- Stay at or under Max rows.
- 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.
Keep the not-certification-advice banner
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 (iso 27001 soa sketch, not certification advice, control inventory soa) 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.