Paste your cover letter, see an Authenticity Score on a 0 to 100 scale, and read which specific sentences carry the AI signal that Workday, Greenhouse, Lever, and iCIMS now flag inside the recruiter view. The score is the headline; the sentence-level colour map is what you actually act on. Cover letters are short and personal, which means small AI patterns matter more than they do on essays. This page is the pre-submission check job seekers run before they send the application: scan the letter, review the highlights, revise the opener and body in your own voice, re-scan to verify the score moved above 80, then submit.
This is the routine active job seekers actually follow before submitting a serious application. The score is the entry point. The sentence-level highlights are where the work happens. Re-scanning is what closes the loop before you hit send.
Open the TextSight detector and paste your full cover letter. The free tier covers 1,500 words per month, which is enough for three to five typical cover letters or several revisions of one. Bracketed placeholders such as [Company Name] or [Hiring Manager] should be replaced with the real values before pasting because some ATS classifiers flag bracketed tokens as template indicators. The scan returns within a few seconds.
The Authenticity Score runs from 0 to 100 where 100 reads fully human to the classifier and 0 reads fully AI. Useful as a summary; not enough on its own. Underneath, the colour map highlights every sentence that tripped one or more signals. Green sentences passed every check. Yellow sentences tripped one or two. Red sentences tripped three or more. Most cover letters have three to seven sentences carrying most of the AI signal, and those are what you act on.
Open your letter alongside the highlights and rewrite the flagged sentences before reaching for any tool. The opener carries the most weight because a recruiter reads it first and decides in three seconds whether your letter sounds like a person or a template. Replace the formula opener with a specific reference: the company, recent news, a podcast episode, a product you actually use, a mutual connection. Cut every "I am excited", "I am thrilled", "I am particularly drawn to". Replace the comma-separated skills triple with one concrete accomplishment carrying a number.
Paste the revised letter back into the detector and re-scan. Aim for 80 or higher on cover letters; the band is tighter than essays because short content amplifies pattern signal. If a single sentence still flags red, go back to step 3 for that one sentence; do not run a Maximum-mode rewrite pass over the whole letter because that flattens the personal motivation the cover letter exists to carry. Then submit through your normal channel. TextSight does not interact with any specific ATS provider and we make no promises about specific outcomes; we report our own score honestly so you can decide if the letter is ready.
A number on its own does not tell you whether to submit. These five bands describe what the classifier is seeing, what major ATS providers tend to do with the same letter, and what the right next move is at each band.
Almost certainly clears the AI-detection layer Workday, Greenhouse, Lever, and iCIMS added through 2025. Recruiters reading the letter will not sense AI patterns either. This is the target band for senior-role and competitive applications where an AI flag meaningfully reduces response rates. Submit through your normal channel and move on.
Most ATS providers will not flag in this range. Recruiters reading the letter usually do not notice AI patterns. For non-competitive roles or roles where recruiter volume is low, this band is fine. If you have time, scan the remaining yellow sentences in the colour map and run one editing pass on the opener and the sign-off; those are the two highest-leverage edits for moving from 75 to 85.
Roughly 30 to 50 percent of ATS classifiers in this range will surface an AI-suspect flag on the recruiter view. Recruiters who use AI-detection browser extensions may see the flag too. Edit the red sentences using the four cover-letter-specific fixes (specific opener, cut enthusiasm phrases, concrete accomplishment, specific next step) before submitting to a role you actually want. Two or three targeted rewrites usually move a 60 into the high 70s.
Most ATS providers will flag in this range. Recruiters sorting by AI-flag status will see your application lower in the queue, and the ones who read it will read it with the AI frame already in place. The fix is structural rather than cosmetic. Restructure the letter (drop the template opener, replace generic enthusiasm with specific reasoning, add real references) before resubmitting. A single rewrite pass will not move a score in this band into safe territory.
Almost certainly raw or lightly-edited ChatGPT output. ATS detection will flag this consistently. Recruiters who get the application at all will read it last, if at all. The fix is a complete rewrite from your own thinking about why you actually want the role, not a quick edit. Use the cover-letter AI rewriter on the hardest individual sentences after you have rewritten the structure from scratch.
Cover letters use the same five base signals as the essay scorer, but with weighting calibrated for short-form professional content. Template opener detection and generic enthusiasm density carry the heaviest weight because they are the strongest cover-letter-specific tells.
"I am writing to express my strong interest in the [Role] position at [Company]" and its fifteen known variants. This opener appears in roughly seventy percent of ChatGPT cover letters and is the heaviest-weighted signal in the cover-letter scorer because it is the single highest-leverage tell. A specific reference in the opener (the company's recent product launch, a piece of work the team published, a person you spoke with, a problem the company is visibly working on) is the fix.
"Excited", "thrilled", "passionate", "eager", "particularly drawn to". ChatGPT distributes three to five of these per cover letter. Real humans use one at most, often none. The scorer counts the density per hundred words; cover letters above three enthusiasm tokens land in the yellow-to-red band on this signal alone. Replace each instance with specific reasoning grounded in what the role actually involves.
"With my experience in X, Y, and Z, combined with my passion for W, I am confident I would be a strong fit." This comma-separated triple is a strong cover-letter-specific signal and one of the patterns ATS classifiers learned to flag earliest. The fix is replacing the list with one concrete story carrying a number: a specific accomplishment, a measurable result, a problem you actually solved.
Intro paragraph that expresses interest, qualifications paragraph that lists skills, closing paragraph that requests an interview. ChatGPT's default and detectors learn the pattern. The scorer detects the structure and weights it as a tell. Real 2026 cover letters mix the structure: two paragraphs, four short ones, or no paragraph breaks at all for a punchier read.
"Looking forward to your response", "Thank you for considering my application", "I look forward to discussing how my background aligns with your goals". ChatGPT cycles between six variants on this closing and recruiters know all of them. Replace with a specific next step: a portfolio link, a piece of work you can talk through, a concrete offer to send the post-mortem doc first if that is easier.
All three AI rewriter modes available on every paid plan. Free covers three to five typical cover letters. Active job seekers usually move to Starter or Pro through the full search. 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 →
The detection layer in major applicant tracking systems caught up through 2025. A flagged cover letter can route your application to a lower review tier before a recruiter ever opens it. Here is what changed and what the score predicts.
Workday surfaces a writing-quality flag on the recruiter view. Greenhouse and Lever both expose third-party AI scores through integration partners. iCIMS does similar at enterprise tier. The flag does not always block the application, but it influences ranking inside the recruiter dashboard, and at high-volume employers it can move a candidate from the first review pass to the second or third.
Internal evaluation against the same 400-letter sample we use for the essay scorer shows TextSight Authenticity Score correlates within 10 to 15 percentage points of the ATS AI flag for major providers. It is a directional pre-flight check, not a mirror of any specific classifier. A TextSight score above 80 typically means the ATS will not flag the letter. A score below 50 typically means it will. The 50 to 80 middle band is where the prediction loosens and the sentence highlights matter most for deciding what to revise.
A cover letter is 250 to 400 words. An essay is 800 to 2,000. The signal density per word is roughly three times higher on a cover letter, which means every AI tell carries more weight per sentence. A single template opener can drop the score by 20 points on a cover letter where the same opener on a long essay would drop it by 6. The scorer is calibrated for that density and the bands above reflect it.
The ATS flag is one risk; the recruiter is the other. After reading fifty ChatGPT cover letters in a week, the pattern recognition is automatic. The score helps you catch what the recruiter would catch on the first pass.
Senior recruiters reviewing fifty applications a day make the assessment on the first sentence. By the second sentence the frame is set, and the rest of the letter reads through that frame. Authentic voice in the opening lines is the single highest-leverage edit. The scorer weights template opener detection accordingly: a specific opener that names the company product, the team's recent work, or a real reason for applying moves the score more than any other single change.
Three to five enthusiasm tokens in the body paragraph signal a template to the recruiter the same way they signal one to the classifier. Cut them. Specific reasoning grounded in what the role actually involves reads as a real candidate; generic enthusiasm reads as a placeholder. The score moves accordingly when you make this edit and the recruiter response moves with it.
"Looking forward to discussing how my background aligns with your goals" is the templated close everyone in hiring recognises. Replace it with a concrete offer or a specific next step. A score that lands in the 80 to 90 band after this edit usually does so because the opener and the close were the two biggest sources of pattern signal in the original.
An honest pre-flight check is closer to a careful proofread than to anything else. We want to be explicit about which side of the hiring-trust line this scorer sits on so you can decide whether it fits your situation.
Cover letters you wrote yourself, including ones where you used ChatGPT for outline or polish on a draft you wrote. The thinking is yours, the motivation is real, the accomplishments are real. The scorer catches sentences where assistant register leaked into the prose so the submitted letter reads in your own voice. We score honestly so you can decide what the letter needs.
It is not a tool for fabricating qualifications or pretending you wrote something you did not. The AI rewriter cannot put authentic motivation into a draft that was not yours. If your letter sounds AI because the underlying interest in the role is borrowed wholesale from a template, the scorer will tell you that and no rewrite pass will magically fix it. The most useful thing TextSight can do for that case is point you back to writing about a role you actually want.
The output of a good revision pass should pass a simple test: if the recruiter asked you in an interview to talk for two minutes about the specific reference or story in your cover letter, you should be able to do it confidently. If you cannot, the revision added voice but not substance, and the letter will fail anyway when you reach the interview stage. The score is a draft check, not a substance check.
The full four-fix rewrite workflow for ChatGPT cover letters, with mode selection guidance and before/after.
Open the guide →The sister scorer for academic essays, with five-format calibration and ESL-aware bands.
Open the scorer →For the follow-up email after submitting the application, and for outreach to recruiters or hiring managers.
Open the guide →How the 0 to 100 score is computed and what threshold to aim for across formats and genres.
Read the guide →Authenticity Score, sentence-level highlights, ATS-aware calibration. Free for three to five typical cover letters per month.