Pre-scan ad creative, long-form sales pages, VSL scripts, landing page heroes, and cold email sequences before they ship into paid media. Sentence-level highlights surface the templated openers, generic urgency, and stock ROI claims that get flagged in client review. Built for freelance direct-response copywriters, in-house brand teams, and agency creative pods. Free to try. No card.
Freelance direct-response copywriters running their own roster, in-house brand copywriters working a single voice across a media plan, and agency creative pods shipping ad sets and sales pages across multiple accounts share the same need: a fast pre-launch scan that flags AI-shaped copy before a reviewer, a client, or a quality score does.
Of every writing discipline, conversion copy is the one that ships straight into a paid-media buy, which is exactly where AI-shaped language costs real money. A flat headline does not just read odd, it drags an ad set's quality score and burns budget on impressions that never convert. Meta and Google tightened creative review through 2025, and brand leads now run an Originality.ai or Copyleaks pass on the ad copy and sales page before they release spend. The working 2026 copywriter still drafts with AI assistance, then pre-scans the creative before a single dollar of media touches it.
A solo direct-response writer is usually juggling an ad set for one client, a sales page for the next, and an email launch sequence for a third inside the same week. Pro at $14.99 a month yearly covers that mix with unlimited scans, a 10,000 character paste that swallows a full long-form sales page in one go, and 90-day history that maps onto a typical performance retainer. When a hook flags every time you rework it, the built-in AI rewriter lifts that one stubborn paragraph in Light mode so the tested offer and proof stack stay exactly as they tested.
An in-house copywriter owns one brand voice and spends it across the whole media plan, shipping ad variants, landing heroes, and nurture emails on a weekly cadence. Running a scan before the creative hits the brand-review standup ends the recurring "this reads a bit AI" note from the brand lead before it is ever raised. The PDF export leaves a per-launch paper trail, which is the artefact a CMO asks for when they want to see how the brand is handling AI quality control across an entire quarter of campaigns.
A direct-response or performance-creative pod runs five to thirty copywriters pushing ad concepts, sales pages, and email flows across a roster of paid accounts. Business at $29.99 a month yearly gives the pod five seats on a shared scan history, REST API access to wire the scan into the brief-to-launch pipeline, an audit log, and white-label PDFs carrying the agency mark for the client handoff. Pods that set an Authenticity Score floor on every piece of paid creative tend to standardise on Business inside their first retainer cycle.
A Facebook ad and a long-form sales page are not the same animal. Each copy 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 one number across every piece of creative.
Short-form, three to seven lines of body plus a headline. Chunk size is below the classifier's reliable band, so single ads score noisily. The realistic move is to scan the full ad set as one paste (five to ten variants together) so the model has enough signal to score consistently. Healthy scores on hand-written direct-response ads run 70 to 85. Generic urgency openers and unspecified ROI claims are the recurring flags.
Ninety-character headlines and ninety-character descriptions. Even shorter than Meta. Scan the entire campaign of fifteen headline variants together rather than scoring one headline at a time. The classifier looks at the joint distribution, which is the only stable read on copy this compressed.
Spoken-word script for a video sales letter, typically twelve to twenty-five minutes of read time. Scores well when the script preserves spoken cadence (contractions, sentence fragments, one-word lines) and scores poorly when it slips into written-prose rhythm. Healthy scores run 75 to 90 on a script written from a real interview rather than an outline.
Three to ten thousand words of structured sales argument with hook, story, offer, proof, and close. The headline number averages across the whole page, which masks specific weak slots. Scan the full page first, then re-scan the hook and the close separately, because those are the sections that drift into stock phrasing under deadline pressure.
Short-form pieces below the reliable chunk band. Scan the full sequence (five to seven emails) as one paste rather than scoring one email at a time. Cold-email opening lines are the highest-risk slot because they default to the templated "I noticed that you" register that LLMs produce by default.
Headline, sub-headline, three benefit lines, and a CTA. Structurally similar across the entire SaaS category by convention, so scoring is volatile on the chunk alone. Treat the headline number as advisory and read the sentence highlights. Specific concrete vocabulary lifts these pieces faster than rewriting the whole hero block.
Pro at $19.99 a month standard, $14.99 a month on yearly, is the right fit for freelance and in-house copywriters. Business at $39.99 a month standard, $29.99 a month on yearly, fits agency creative pods 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 →
Copywriting frameworks are not the enemy. A framework filled in with generic language is. AIDA, PAS, and 4Ps produce templated structural moves that overlap heavily with what an LLM defaults to when prompted for a sales page. The fix is to keep the framework intact and load the body with specifics.
Attention, Interest, Desire, Action still works, but the Attention slot is the one that flags hardest. Generic openers (Imagine, Picture this, Unlock, Discover) read as templated to both reviewers and classifiers. Replace the slot with a specific number, a named customer, or a verbatim quote from research, and the framework slot still does its job without the AI fingerprint.
Problem, Agitate, Solve scores best when the Agitate slot uses concrete customer-voice phrasing instead of generic "you are tired of struggling with" language. The structural move is fine. The vocabulary is the giveaway. Sentence highlights show which Agitate lines dropped into the templated band so you can swap in research-derived phrasing surgically.
Promise, Picture, Proof, Push relies on parallel structure across the four slots. LLMs produce parallel structures by default, so a Four Ps page often flags hard if the slots are all the same sentence length and cadence. Vary the rhythm between slots (short, long, fragment, long), add specific proof figures, and the framework reads human while still delivering the rhythm readers expect.
The recurring offending openers are Unlock, Discover, Transform, Elevate, Revolutionise, and Master. They flag in headline scans because they sit in the templated band of LLM defaults. Healthier openers lead with a specific noun, a number, or a verbatim quote pulled from research. The discipline is to write the opener last, after the offer and proof are settled, so it can carry specific content rather than acting as a generic warm-up.
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 brand lead and read human to the classifier. The pieces that flag are usually the ones where a writer dropped into the neutral SaaS register to push through a deadline.
The same swipe-file move that wins on conversion wins on the detector. When the body of a sales page or an email is built from review-mining, sales-call recordings, and support-ticket language, the vocabulary is so specific to that buyer that no model would default to it. Pulling verbatim customer phrases into the draft pays twice: it sharpens the offer and it pushes the Authenticity Score up at the same time, because specificity is precisely what the classifier reads as human.
A brand book that bans generic category language and insists on the product's own naming and proof points is, in effect, asking for copy that reads less templated. The conversion brief and the detector want the same thing. Hit the brand's mandated vocabulary and the score climbs as a by-product of writing the offer the way the brand actually positions it.
Some brands lock a fixed sign-off, a legal disclosure, or a stock guarantee line that will score low no matter who writes it because it is, by design, formulaic. Call it out in the kickoff so the brand lead expects that slot to read lower than the body, and defend it as a required, non-negotiable element rather than reworking copy you are contractually obliged to ship verbatim.
On conversion copy the score is a diagnostic, never the target. Rewriting a tested headline or close purely to lift a percentage is how a writer flattens the exact phrasing that was carrying the click-through. Use the sentence highlights to isolate the lines that genuinely drifted into stock phrasing, fix those, and leave a proven hook alone even if it sits a few points lower. The conversion holds and the asset still clears the floor.
A pre-handoff scan is the move that keeps brand leads from running their own check and asking awkward questions on the review call. Build the scan into the delivery ritual so every piece of copy ships with a screenshot of the score and the date in the email or Slack thread.
A throwaway organic caption and a sales page about to carry a five-figure media budget do not deserve the same bar. Direct-response pods usually set the Authenticity Score floor higher on the assets that touch paid spend (the sales page, the VSL, the ad set) and looser on low-stakes social. Name the floor per asset type in the kickoff so a writer who pastes a 72 sales page knows to rework the hook before it ever reaches the media buyer. Consistency on the paid pieces is what stops a brand lead from quietly running their own check the night before launch.
Drop a screenshot of the score and timestamp into the launch thread alongside the ad copy and the landing URL, or attach the Pro and Business PDF export to the creative handoff. The goal is to clear the AI question while the campaign is still in staging, not after the ad set is live and an impression spend is already running. Once a brand lead sees one launch arrive pre-cleared, they stop gatekeeping every subsequent ad concept on an AI suspicion.
Performance copy multiplies fast: one control spawns five headline tests, and a "make it punchier" note can quietly reintroduce stock urgency. Rescan each variant and each post-feedback revision before it enters the rotation, so a templated line never slips into a test cell and muddies which hook actually moved the conversion rate. Keeping a scan on every variant means a late detector flag never lands on creative that was already in market.
The Business audit log records which copywriter scanned which asset, the timestamp, and which scans were exported for client handoff. In a monthly performance review it lets the pod show that every piece of paid creative cleared the same AI bar before it touched media budget, rather than leaning on one senior writer's gut read at launch time.
A high score is not the win condition on its own. The win condition is copy that converts and does not get flagged. Use the score as one diagnostic alongside open rate, click rate, and conversion rate rather than chasing the headline number at the expense of a tested control.
On a control that is already converting, the right AI rewriter setting is Light. It preserves sentence structure and only adjusts cadence, which means the tested hook, offer, and close stay intact while the AI fingerprint comes off. Maximum mode is reserved for stock phrasing that was templated to begin with and was never a tested element.
When generating A/B variants from a winning control, scan each variant before launch and discard anything that scores below the floor. This prevents a generative-AI variant from polluting the test cell and giving you a false read on whether the new hook is the issue or the AI residue is.
Subject lines and preheaders are the highest-AI-risk slots in an email sequence because they default to templated curiosity ("You will not believe what happened next") and templated urgency ("Last chance, ending tonight"). Scan subject-line variants in batches of ten or twenty so the chunk is big enough to score reliably, then pick the highest-converting one that clears the score floor.
Landing page heroes correlate strongly with hero-level conversion rate. A hero that reads generic ("Transform your business with our platform") sits low on both score and conversion. A hero with a specific number and a named customer ("Cut onboarding from twelve days to three for Series B SaaS") sits high on both. The detector is reading the same flatness signal the visitor reads.
A single percentage tells you nothing about which line to rewrite. The TextSight result panel breaks the asset down to the sentence, with paragraph rollups for long-form pieces, so you can fix the one flagged hook or CTA instead of redrafting copy that already converts.
Every line is colour-coded by its own AI-likeness score, which on conversion copy usually means one offending headline, urgency line, or CTA lights up rather than the whole asset. A cluster of red across the opening of an ad is a real signal; a scattered yellow on a stock connective phrase mid-body rarely is. You read the pattern and rework the specific line, not the offer.
On long-form assets the rollups show which block is dragging the headline score. On a sales page it is almost always the hook or the close that drifted under deadline; on a VSL script it is the bridge from problem to solution; on an email it is the subject and the opening line. Fix the lowest-scoring block first and the whole asset lifts without touching the parts that already test well.
Perplexity measures how predictable your word choices are to a language model, and low perplexity reads AI-like. Shown per sentence on Pro, it is the context that tells you whether a flagged benefit line is genuine AI residue or just a tight, conventional product claim that a real copywriter would write the same way.
Burstiness is how much sentence length and rhythm swing across the copy. An LLM defaults to uniform, medium-length lines, while strong direct-response copy is deliberately bursty: a one-word punch, a long benefit run-on, a fragment for the turn. Flat, even cadence across an ad or sales page is the tell a seasoned media buyer or brand lead clocks before any tool does.
More for copywriters.
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 copywriters; Business at $29.99 a month on yearly for agency creative pods.
How TextSight fits other teams and workflows.