How to Build a Competitive Feature Matrix from Pasted Docs
Feature matrices lie when silence becomes a no and a dollar appears from a page you did not paste. Unknown stays unknown. Not a pricing teardown.
The matching generator is the Competitive Feature Matrix from Pasted Docs (No Invented Features) 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).
Columns only for names you listed
Build a competitor feature matrix from pasted docs only. No invented features, prices, or scores. 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:
Our product name: [Ours]
Competitor names I may use (as pasted): [Names]
Pasted doc excerpts per competitor: [Docs]
Feature rows I want (must be findable in Docs): [Rows]
Scoring I allow (or NONE): [Score]
Prices I may print (or NONE): [Prices]
Date I retrieved the docs: [Date]
What I must never infer: [Never]
Words I must not use: [Banned]
Unknown policy: [Unknown]
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.
Yes cells need a quote from the paste
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: ours, names, every feature row, prices, date. Forbidden: features and prices not in Docs.
- Matrix: rows = Rows, columns = Ours plus Names. Cell values: quoted evidence or Unknown policy.
- Evidence: a short quote per yes cell. If the paste does not support the row, mark unknown, never yes.
- Prices: only Prices. If NONE, omit a price row even if Docs mention a number you did not copy into Prices.
- Scores: only Score. If NONE, no 1-5 ratings.
- Date stamp: Date on the matrix. Do not fetch live pages.
- Gaps: rows with all unknown.
- Compliance pass: quote Banned words, invented SSO, invented list prices. Cut them.
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.
Unknown policy beats a guessed no
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:
- Feature matrix from pasted docs. Not a pricing teardown, not ads, not positioning prose.
- Never invent a feature, price, or score.
- Unknown stays unknown.
- Do not browse. Docs only.
- 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.
No scores or prices unless you allowed them
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 (competitive feature matrix, competitor features from docs, no invented features) 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.