AI detector for blog posts, and what a high score actually means

Paste the post into the checker above and you get a 0-100 AI score plus one of three verdicts: reads as AI-generated, borderline, or reads as human-written. It is free, 10 credits a day per network, and a check costs 1 credit whatever the length, so a 400-word news item and a 2,500-word guide cost the same single credit. The minimum is 65 words. No account, no login, no card, no email address. Then read the number for what it is. It is not a ranking penalty waiting to happen, and it is not a verdict on who wrote the post. It is a reading of how closely your draft resembles the average of everything already written on your topic, and that resemblance is the thing worth fixing before you publish.

Try an example:
113 words
This run costs 1 · 10 of 10 free credits left today

What the score is telling you, and what it is not

The reading describes how densely certain patterns appear in the text you pasted. It is an editorial signal about the writing. It is not a prediction of what a search engine will do with your page, and it is not a prediction of what a different detector will report on the same paragraph. No tool can tell you that from the outside.

Google publishes its own guidance on AI-generated content, and the short version is that helpful content is rewarded regardless of how it was produced, while pages mass-produced to game search are treated as spam. Read it at the source rather than acting on anyone's summary, including this one. The split it draws is the part that matters to you: a page built to occupy a keyword is one thing, and a useful post that happened to start as a model's draft is another.

What the score does track well is sameness. Generated drafts converge on the middle of what has already been written about a topic, because that is what the model learned from. A reader who already has three tabs open on the same query recognises the fourth quickly and leaves. That behaviour costs you more than the score does.

Why generated blog drafts come out generic

Ask a model for a post on a topic and it returns the consensus of everything written on that topic before, with the specifics filed off. Every claim is one that was safe to make in general, which means every claim is one your competitors have already made.

The missing ingredient is first-hand material: the number from your own dashboard, the price you actually paid, the thing that broke when you tried it, the sentence a customer said on a call. A model has none of that, so it fills the space with reasoning about the topic instead of information from inside it.

The second cause is the skeleton. Generated posts follow one outline. Define the term, explain why it matters, list three benefits, give numbered steps, list common mistakes, close by restating the headings. That shape is acceptable on a definition page and deadly on any query where you have a view worth reading.

The tells that show up in blog drafts

These are the patterns that push a score up, and they are also the lines a good editor deletes first.

The AI vocabulary checker marks this vocabulary in your own draft. It runs in your browser, costs no credits and has no daily limit, so you can paste a working draft into it as often as you like while you edit. The AI writing tells reference sets out the wider patterns with the reasoning behind each one.

  • An opening paragraph about the growing importance of the topic that promises what the article will cover and makes no claim of its own.
  • A heading that repeats the search query word for word, followed by a first sentence that repeats the heading.
  • Everything arriving in threes. Three benefits, three challenges, three best practices, whether or not there are three.
  • Sentences that all land at roughly the same length, one balanced clause after another, with no short ones between them.
  • Vocabulary that gives it away on sight: delve, leverage, robust, seamless, underscore, moreover, furthermore, in today's landscape, navigate the. Cut every one.
  • Claims wearing a hedge instead of a source: studies suggest, many experts agree, research has shown. If you cannot name and link the study, delete the sentence.

The edits that fix the post, not just the score

Do these in order, because the first one changes what the rest of the post is able to say. Adding information beats rearranging sentences every time, and it is the only edit that also helps the page compete.

  • Put something in the first 150 words that could only come from you. A figure from your own analytics, a result you got, an amount you spent, a mistake you made.
  • Delete the introduction and start at the first sentence that makes a claim. Most generated intros can be removed whole with nothing lost.
  • Answer each heading in the sentence directly below it, then support the answer. Do not restate the heading.
  • Take a side. Say which option you would pick and why the other two lose. Models hedge because they cannot commit, so commitment is the cheapest way to sound like a person.
  • Break the rhythm on purpose. One short sentence every few paragraphs. It works.
  • Add one thing a competitor would have to redo the work to copy: a table of numbers you gathered, a screenshot, a quote from someone who spoke to you.

Running the check across a whole post

A check costs 1 credit whatever you paste, so length never costs you anything. What spends credits is splitting the post up. The whole thing in one go is one credit, and the same post checked section by section is one credit per section.

Ten credits a day covers ten checks, which is enough to map a long post and still re-check the parts you rewrote. Word counts come from the free word counter, and the readability checker will tell you whether the sentences have gone stiff. Neither costs a credit.

  • One check on the full post for a baseline. Note the score and the verdict.
  • One on the introduction alone, if it clears 65 words. Intros carry more tells than any other part of a post.
  • One on the conclusion, for the same reason.
  • One per major section on anything long enough to split. The pattern across sections is the finding, not any single number.
  • Leave out pull quotes, block quotes and anything you did not write. Those score somebody else's sentences.

Rewriting a post, and where the credits actually go

The humanizer rewrites every sentence in one click. A run takes 12,000 characters, roughly 2,000 words, with a 25-word minimum, and it costs 1 credit per 50 words. A 1,500-word post is therefore 30 credits, which is three free days.

The better move is to spend the credits where the tells are. Rewrite the introduction and the conclusion, usually 300 to 500 words together and six to ten credits, then fix the body by hand with the free tools. Body sections built from material you supplied are rarely where the problem sits.

One thing to get right about the order: add your first-hand facts before you rewrite, not after. A rewrite works only from the text you hand it, so a draft with nothing specific in it comes back as a rewritten draft with nothing specific in it. The sentences change and the reason to read the page never appears.

If a client or an editor says your post reads as AI

Detectors measure style, not authorship. Clean, orderly, correct prose scores high whoever produced it, which is exactly what a professional writing to a house style produces. It falls hardest on people writing in a second language. Stanford HAI researchers (Liang et al., 2023) ran TOEFL essays by non-native English speakers through seven detectors and found 61% falsely flagged as AI-generated. Every one of those essays had a human author.

For evidence, the signed drafting record captures the shape of a writing session: when you worked, how much you cut and rewrote, and whether anything large arrived in a single paste. It signs that record with an ECDSA P-256 key and commits it to your exact text with a hash, so anyone can check the signature and the match on the verify page without contacting us. It records forward, so start it on the next post rather than the one already delivered. The plagiarism and originality check answers the separate question of whether your text overlaps published sources.

On the rules, briefly. Rewriting a draft you were permitted to generate is ordinary editing. Where a client contract or a publication's guidelines say AI-generated text is not permitted, that covers the draft however it was edited afterwards. Read the agreement you are publishing under.

Questions people actually ask

AI detector for blog posts, and what a high score actually means: common questions

Does Google penalise AI-generated blog posts?

Google's published guidance on AI-generated content is the document to read, and the short version is that helpful content is rewarded regardless of how it was produced, while pages mass-produced to game search are treated as spam. That is as far as we will go, because the rest would be guesswork. The practical version: a page that exists only to occupy a keyword is the exposure. A page carrying something a reader cannot get anywhere else is not, whatever wrote the first draft.

Will a high AI score here hurt my search rankings?

The score is not a search signal and it does not travel anywhere. It measures how densely certain patterns appear in the text you pasted, and it cannot tell you what a search engine or any other detector will conclude about your page. Use it as an editorial read on whether the draft sounds like everything else already ranking for the query.

What does it cost to check a 2,000-word post?

One credit. Checking is flat-priced whatever the length, so a 2,000-word guide and a 200-word introduction cost the same. The free allowance is 10 credits a day per network with no account, no card and nothing to verify, and the checker needs at least 65 words.

Can I humanize a full 1,500-word post for free?

Not in a single day. One run holds 12,000 characters, about 2,000 words, so a 1,500-word post fits comfortably in one run, but rewriting costs 1 credit per 50 words and 1,500 words is 30 credits against an allowance of 10 a day. Either run it across three days, or spend the credits on the introduction and conclusion where the tells cluster and fix the rest by hand with the free tools.

Will the humanizer keep my statistics and examples?

It rewrites the sentences you paste and works only from what is in them, so it has nothing to add and nothing to look up. Read the result once against your notes before publishing. And put the specifics in first, because a draft with no first-hand material comes back with no first-hand material.

A client says my post reads as AI. What do I actually send them?

Start with what you already have: document version history, dated drafts in email, research notes, interview recordings, the screenshots you took while working. Then add a signed drafting record for the work you do from here, which gives timestamps and revision behaviour that a third party can verify independently on the verify page. Nothing proves authorship on its own, but specifics answer an accusation far better than a denial does.

Should I disclose that a post was drafted with AI?

That depends on the agreement you are publishing under. Client contracts and publication guidelines are the documents that decide it, and some ask the question directly on the brief. If yours asks, answer it honestly.

Keep reading