What the rubric measures
The rubric scores a finished piece of AI-written or AI-assisted content for whether it is fit to publish. It does not try to detect whether AI wrote the text. It measures quality, accuracy and risk, the things a client pays an editor to guarantee.
Unit of review: one piece (article, page, email, product description). Pieces over 3,000 words are scored in sections of up to 3,000 words and the lowest section score is reported.
Scoring method
- Score each of the 7 dimensions from 0 to 4 using the descriptors below.
- Points for a dimension = weight × (score ÷ 4).
- Add the points for a total out of 100.
- Check the critical fails. Any critical fail caps the result at "Fail", whatever the total.
- Record every issue found on the score sheet with its location, so the score can be checked and the fixes made.
Result bands
| Total | Result | Certificate |
|---|---|---|
| 90–100 | Verified, excellent | Yes |
| 80–89 | Verified | Yes |
| 65–79 | Needs editing | No, re-score after edits |
| 0–64 | Fail | No |
Critical fails (automatic Fail)
- A fabricated fact, statistic, quote, person, study or source.
- A claim that creates clear legal risk: defamatory, a health, financial or legal claim without support, or copied text without permission.
- Content that contradicts the client's brief on a point the brief marks as required.
- Placeholder or prompt text left in the piece ("As an AI…", "[stat needed]", "Certainly! Here is…").
The 7 dimensions
1. Accuracy and sourcing (weight 20)
Are the claims true, current and supported?
| Score | Descriptor |
|---|---|
| 4 | Every checkable claim is correct. Statistics, dates and names are sourced or easily verified. No outdated information. |
| 3 | One minor inaccuracy or unsourced claim that does not change the meaning. |
| 2 | Two or three minor inaccuracies, or one claim that misleads on a secondary point. |
| 1 | Several inaccuracies, or one that misleads on a main point. |
| 0 | Accuracy cannot be relied on. |
Method: list every checkable claim. Verify at least the 5 most important, or all if fewer than 5.
2. Fit to brief and audience (weight 10)
Does the piece do the job it was commissioned for?
| Score | Descriptor |
|---|---|
| 4 | Meets every point in the brief. Right length, reading level, keywords and call to action for the stated audience. |
| 3 | Meets the brief with one small gap. |
| 2 | Misses one important point or pitches to the wrong level in places. |
| 1 | Misses several points, or the audience is clearly wrong. |
| 0 | Does not answer the brief. |
If no brief exists, score against the stated or obvious purpose and note "no brief".
3. Clarity and structure (weight 15)
Can the reader follow it and find what they need?
| Score | Descriptor |
|---|---|
| 4 | Logical order, clear headings, one idea per paragraph, strong opening and close. No passage needs a second read. |
| 3 | One or two passages are unclear or out of order. |
| 2 | Structure works but several paragraphs wander or bury the point. |
| 1 | Hard to follow; reader must work to extract the main points. |
| 0 | No usable structure. |
4. Language correctness (weight 15)
Grammar, spelling, punctuation, usage and consistency (capitals, numbers, hyphenation, UK/US spelling).
Score by errors per 1,000 words:
| Score | Errors per 1,000 words |
|---|---|
| 4 | 0–1 |
| 3 | 2–3 |
| 2 | 4–6 |
| 1 | 7–10 |
| 0 | More than 10 |
Count each error once even if repeated, but count each inconsistency (for example "e-mail" and "email" in one piece) as one error.
5. Style and voice (weight 10)
Does it sound like the client and follow their house style?
| Score | Descriptor |
|---|---|
| 4 | Consistent tone that matches the client's voice and style guide. Varied sentences. |
| 3 | Tone slips once or twice. |
| 2 | Generic voice; could belong to any company. |
| 1 | Tone is wrong for the brand or audience in several places. |
| 0 | Voice works against the brand. |
6. AI writing patterns (weight 20)
The habits that make AI text read as unedited and cost trust. Count instances of:
- Filler and throat-clearing ("In today's fast-paced world", "It's important to note").
- Stock phrases and clichés common in AI output ("delve", "unlock the power of", "navigate the landscape", "game-changer").
- Empty hedging or empty superlatives.
- Repetition: the same point, phrase or sentence pattern restated.
- Formulaic structure: every section the same length and shape, list-heavy text where prose fits, a summary that repeats the body.
- Vague specifics: invented-sounding examples, "studies show" with no study.
- Over-formatting: bold and bullets used for emphasis rather than meaning.
| Score | Instances per 1,000 words |
|---|---|
| 4 | 0–2, and the piece reads as written by a person who knows the subject |
| 3 | 3–5 |
| 2 | 6–9 |
| 1 | 10–15 |
| 0 | More than 15 |
7. Risk and compliance (weight 10)
Could publishing it cause legal, regulatory or reputational harm?
| Score | Descriptor |
|---|---|
| 4 | No risk found. Claims are qualified where needed. Required disclosures (AI use, affiliate links, sponsorship) are present. |
| 3 | One low-risk wording issue. |
| 2 | A missing disclosure or an over-strong claim that needs softening. |
| 1 | Several risk issues. |
| 0 | Serious risk. Also triggers a critical fail if it meets the critical-fail list. |
EditorVerified does not give legal advice. Check disclosure rules that apply to you with your own adviser.
Score sheet (one per piece)
| Field | Entry |
|---|---|
| Client / piece title | |
| Word count | |
| Brief supplied? | Yes / No |
| Reviewer (named editor) | |
| Date | |
| 1. Accuracy (×20) | score __ / 4 → __ pts |
| 2. Brief fit (×10) | score __ / 4 → __ pts |
| 3. Clarity (×15) | score __ / 4 → __ pts |
| 4. Correctness (×15) | errors __ per 1,000 → score __ → __ pts |
| 5. Style (×10) | score __ / 4 → __ pts |
| 6. AI patterns (×20) | instances __ per 1,000 → score __ → __ pts |
| 7. Risk (×10) | score __ / 4 → __ pts |
| Critical fails | None / list |
| Total | __ / 100 |
| Result | Verified excellent / Verified / Needs editing / Fail |
| Issue log | location, dimension, issue, suggested fix |
