Home/Blog/How to Write an ADR from a Design Chat Paste
Blog

How to Write an ADR from a Design Chat Paste

P
promptstudio
How to Write an ADR from a Design Chat Paste

ADRs invent options nobody discussed. Quote the chat. Leave OWNER UNKNOWN when blank.

The matching generator is the ADR Architecture Decision Record from a Design Chat Paste (Facts Only) (Adr Architecture Decision Record From A Design Chat Paste Facts Only) 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).

Lock title status owner and date from Inputs

Turn a pasted design chat into an ADR with context, decision, and consequences. Facts only. Never invent options or owners. 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 design chat or notes: [Chat]
Decision title I allow (or UNKNOWN): [Title]
Status I allow (Proposed/Accepted/Deprecated or UNKNOWN): [Status]
Owner I allow (or UNKNOWN): [Owner]
Date I allow (or UNKNOWN): [Date]
Words I must not use: [Banned]
What I must never invent: [Never]
Output format: [Format]
Language: [Lang]

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.

Write context only from the pasted chat

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:

  1. Honesty ledger: Chat nouns, Title, Status, Owner, Date, Lang. Forbidden: invented options, invented owners, invented tickets.
  2. Title line: Title or TITLE UNKNOWN.
  3. Status and Date: quote Status/Date or UNKNOWN.
  4. Context: 3-6 sentences quoting only Chat. No invented outages.
  5. Decision: one paragraph of what was chosen in Chat. If Chat is ambiguous, write DECISION UNCLEAR IN CHAT.
  6. Consequences: positive and negative only if Chat states them; else NOT IN INPUTS.
  7. Alternatives considered: only options named in Chat. Do not invent Redis vs Postgres debates.
  8. 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.

List alternatives only if the chat named them

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:

  • ADR from Chat only. Not an RFC and not a code scaffold.
  • Never invent options, owners, or ticket IDs.
  • Keep Owner/Date UNKNOWN when blank.
  • 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 ticket IDs and owners

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 (adr architecture decision record, design chat paste facts only, architecture decision record template) 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.