Pre-scan blog posts, landing pages, product copy, and email sequences before they leave your editor. Sentence-level highlights show which lines drift into stock phrasing, with perplexity and burstiness signals so you can fix the prose instead of arguing about a number. Built for solo freelancers, in-house content writers, and agency teams shipping volume. Free to try. No card.
Solo freelance writers shipping pieces to direct clients, in-house content writers running a brand blog, and agency writing teams scaling volume across multiple clients all share the same need: a fast pre-delivery scan that flags AI-shaped prose before a content lead does.
Content writing is one of the broadest categories in the writing market and one of the most exposed to AI review. Marketing teams have learned to spot AI prose. Originality.ai and Copyleaks scans are a normal part of a paid-content QA cycle. The realistic 2026 workflow uses AI assistance and pre-scans the output for delivery.
Five to fifteen deliverables a week across two to five direct clients. Pro at $14.99 a month yearly gives unlimited scans, 10,000 character pastes, and 90-day history covering roughly the length of a single client engagement. The integrated AI rewriter handles the stubborn paragraphs that flag every time without forcing a full rewrite.
One or two writers running a brand blog plus a landing page roadmap. Pre-scanning every piece before it goes to legal review or to the CMS cuts the AI-pushback loop with marketing leadership. The PDF export keeps a defensible record per article, useful when leadership later asks how the content team is handling AI quality control.
Five to thirty writers shipping fifty or more deliverables a month across multiple client accounts. Business at $29.99 a month yearly unlocks five seats with shared scan history, REST API access for workflow automation, an audit log, and white-label PDFs branded to the agency. Most content agencies running a minimum Authenticity Score policy settle on Business within their first quarter.
A blog post and a landing page hero are not the same animal. Each content genre has its own register, its own paraphrase density, and its own false-positive risk. Read the score in context of the format rather than chasing a single number across every type of work.
Fifteen-hundred to three-thousand words of structured argument with an intro, scannable subheads, and a closer. Healthy scores run 75 to 90 on prose written from a real outline and your own voice. The intro and the closer are the highest-risk paragraphs because both default to stock phrasing when drafting moves fast. Scan the full piece, then re-scan the intro and closer alone if the headline number is borderline.
Numbered or bulleted format where every item gets a short paragraph of supporting prose. Listicles tend to score lower because the per-item paragraphs all follow the same structural rhythm. Healthy scores run 65 to 80. Sentence-level highlights matter more than the headline here because the issue is usually two or three flat items, not the whole article.
Tutorial content with explicit numbered steps and standard transitional phrasing. Reads templated for the same reason a methods chapter does: a sequence of identical structural moves. Scores tend toward 60 to 75. The defence is varied step-intros and concrete first-person examples woven through, both of which read human to the classifier and read useful to the reader.
Short, punchy, and structurally similar across the entire SaaS category by convention. Scoring is volatile because the chunk is small. Treat the headline number as advisory and read the sentence highlights instead. Specific concrete vocabulary and varied sentence length lift these pieces faster than rewriting the whole block.
Short-form pieces where the chunk size is below the classifier's reliable band. Single emails and single captions score noisily. Scan the full sequence as one paste or batch ten captions together so the model has enough signal to score consistently.
Pro at $19.99 a month standard, $14.99 a month on yearly, is the right fit for solo freelancers and in-house writers. Business at $39.99 a month standard, $29.99 a month on yearly, fits agency teams scanning fifty or more deliverables a month. Full details on the pricing page.
Billed $89.88/year — Save $30
Billed $179.88/year — Save $60
Billed $359.88/year — Save $120
Yearly billing saves 25%. View full pricing →
A pre-delivery scan is the move that keeps clients from running their own Originality.ai or Copyleaks check and asking awkward questions about the result. Build the scan into the delivery ritual so every article ships with a screenshot of the score in the email.
Most agencies settle on an Authenticity Score floor of 75 or 80 for client work. Communicate the policy in the kickoff doc so a writer sending a 72 knows to revise before submitting. The number itself matters less than the consistency: a stable floor across every deliverable signals to the client that quality control runs the same way every time.
Paste a screenshot of the score and the timestamp into the body of the delivery email, or attach the PDF export on Pro and Business. The point is to pre-empt the conversation. Once a client receives one delivery with the scan attached, they stop running their own check on every subsequent piece because the trust is established.
If the client requests substantive edits, rescan the revised piece and reattach the new report. This catches the case where a revision accidentally drops the score by introducing a flat templated passage to fix a different issue. Keeping receipts on the revision cycle prevents a late-stage flag from coming out of nowhere on a piece that scanned clean originally.
The audit log on the Business tier shows which writer scanned which deliverable, with timestamps, and which scans were exported as PDFs. Useful for quarterly client reviews where the agency wants to demonstrate consistent AI-quality control across the writing team rather than relying on individual judgment.
A high Authenticity Score with green sentence highlights across the body is a stronger position than a one-line "scanned clean" claim. When a client raises a flag from a third-party detector, walk through the specific paragraph and explain the register rather than arguing the headline number.
The TextSight result view colour-codes every sentence by its own AI-likeness score. A client looking at scattered yellows in otherwise green prose sees the same thing a content lead sees: a piece that reads structured and on-register, not a piece that was drafted by a model. The visual is the argument.
If a client comes back saying a competing detector flagged paragraph four, pull up the TextSight scan for that paragraph and walk through the sentences. Stock-phrased intro? Rewrite it. Genuinely human prose that happened to land in the templated band? Defend it with the perplexity and burstiness signals and the contemporaneous scan record.
A scan report plus drafting notes (outline, research links, version history in Google Docs) is a stronger position than either alone. The scan handles the prose-level question; the drafting notes handle the authorship question. For high-value direct clients and platform disputes, having both means you rarely lose the conversation.
Brand voice and detector pass-through line up more often than they fight. Distinctive cadence, varied sentence length, and concrete vocabulary all read on-brand to a content lead and read human to the classifier.
Brand voices built around a specific cadence (short sentences in a tech brand, long ones in a financial publication) score well because they vary structurally from the templated AI default. The pieces that flag are usually the ones where the writer dropped into a neutral SaaS register to push through a deadline. Catching that drift on a scan is the diagnostic.
A style guide that says "use product-specific terms instead of generic SaaS language" is also asking for prose that reads less templated. The two requirements collapse into one. Following the brand vocabulary lifts the detector score as a side effect.
Rare, but it happens. Some style guides require highly formulaic intro openers or sign-offs that flag every time. The right move is to flag this in the kickoff so the client knows the intro paragraph will run lower than the body, then defend the formula on its merits rather than rewriting it.
The score is the diagnostic, not the goal. Rewriting a piece purely to lift the number tends to flatten the voice. Use the sentence highlights to find specific lines that drift into stock phrasing, rewrite those, and let the headline number land wherever it lands. The brand voice survives and the deliverable still passes.
A single percentage is not a fix path. The TextSight result panel shows which sentences reacted and why, with paragraph-level rollups for longer pieces, so you can edit specific lines instead of rewriting the whole article.
Every sentence is colour-coded by its own AI-likeness score. Red sentences clustered in one paragraph are a stronger signal than scattered yellows. Scattered yellows in otherwise structured prose often just mean a stock transitional phrase. You read the pattern, not just the headline number.
Longer pieces get paragraph-level rollups so you can see which paragraph is dragging the headline score. The intro and the closer are the usual suspects on blog posts, while the per-item paragraphs are the usual suspects on listicles. Targeting the lowest paragraph first is the fastest way to lift the article.
Perplexity is how predictable your word choices are to a language model. Low perplexity reads AI-like. The score is shown per-sentence on Pro, which is the diagnostic context you need to decide whether a flag is real AI residue or a particularly well-rehearsed product description.
Burstiness is how much your sentence length and structure vary across the piece. ChatGPT defaults to uniform medium-length sentences. Real human writing has bursty rhythm: one short sentence, one long, one fragment. Low burstiness across an entire article is the classic AI fingerprint and the one content leads learn to spot first.
More for content writers.
The full content-writer workflow with delivery-attached scans and brand voice defence.
For writers →How agency teams running fifty-plus pieces a month build the scan into their QA workflow.
For agencies →Light, Balanced, and Maximum modes for fixing flagged passages without losing voice.
Read the guide →Free, Starter, Pro, Business. Yearly billing saves 25%. Solo to agency tiers.
See pricing →Free to try. No card. Pro at $14.99 a month on yearly for solo writers; Business at $29.99 a month on yearly for agency teams.