An AI-written resume has a quiet problem: it reads generic. Same flashy verbs, same vague impact lines, same uniform bullets that a recruiter has seen on a hundred other applications this week. Paste your resume, get an Authenticity Score on a 0 to 100 scale, and see which bullets read AI to the classifier and to a human reader. The number is the summary; the per-bullet colour map is what you fix. Resumes concentrate the signal more than any other document because each bullet is short, rigid, and surrounded by other short bullets, which is why a strong STEM resume and a hard-working recent-grad resume can both score low on the first scan even when every line is true. The job is not to hide your experience. It is to keep your real work and strip the borrowed phrasing on top, so the page reads like a person who actually did the job.
This is the routine job seekers follow before sending a tailored application. Bullet by bullet, the goal is to keep the real work and remove the generic phrasing layered on top. The score points you at the weak lines; the editing is yours.
Open the TextSight detector and paste the full text of your resume, header through Education. The free tier covers 1,500 words per month, which is enough for two to four typical resume versions or several revisions of one master document. Replace any bracketed placeholders such as [Company], [Result], or [Percentage] with the real values first, since an unfinished template reads worse than a finished one. The scan returns in a few seconds.
The Authenticity Score runs from 0 to 100 where 100 reads fully human to the classifier and 0 reads fully AI. Treat the number as a summary. The colour map underneath highlights every bullet that tripped one or more signals. Green bullets passed every check. Yellow bullets tripped one or two. Red bullets tripped three or more. Most resumes have five to twelve bullets carrying most of the AI signal. Those are what you act on, in that order: red first, yellow second, green left alone.
Open your resume alongside the highlights and rewrite the flagged bullets before reaching for any tool. The single biggest practical lever is quantified-impact specificity. A bullet that names the tool, the team size, the time frame, and the percentage move will almost always score human-likely, because the specificity is the signal that LLMs hallucinate worst. Replace cycled action verbs with the verb that actually describes the work. Replace vague impact phrasing with the real number, even if the number is small. Replace skills-list bullets with one concrete project that demonstrates the skill.
Paste the revised resume back into the detector and re-scan. Aim for 80 or higher on resumes; the band is tighter than essays because each bullet concentrates signal. If a single bullet still flags red, go back to step 3 for that one bullet; do not run a Maximum-mode rewrite pass over the whole resume because that flattens the specifics that make the resume work in the interview. Then submit through your normal channel. TextSight does not interact with any specific ATS provider and we make no promises about specific application outcomes; we score honestly so you can decide whether the resume is ready.
A number on its own does not tell you whether the resume is ready. These five bands describe what the classifier is seeing on your bullets and what the right next move is at each one.
Very few bullets read generic. A recruiter scanning the page sees specific, lived-in work rather than template phrasing. This is the band worth holding out for on senior and competitive roles, where a resume that sounds like everyone else's quietly slides to the bottom of the pile. Send it and move on to the cover letter.
Most bullets read human. For non-competitive roles this band is fine as is. If you have time, scan the remaining yellow bullets and run one editing pass on your most recent role, because those are the bullets a recruiter reads first and weighs hardest. They are the two-minute edits with the highest payoff for moving into the mid-80s.
Enough bullets read generic that the resume risks blending into the stack. This is where most STEM and recent-grad resumes start even when every line is true, so it is not a verdict on your honesty, only on the phrasing. Edit the red bullets with the four resume fixes (quantified impact, specific tool, named project, the plain verb that describes the work). Two or three targeted rewrites usually lift a 60 into the high 70s.
Most bullets carry the generic AI pattern, and the resume reads more like a template than a career. The fix is structural rather than cosmetic. Drop the cycled action verbs, replace vague impact lines with real numbers, and swap skills-list bullets for specific stories before resubmitting. A single rewrite pass will not move a score in this band into safe territory.
Almost certainly raw or lightly-edited model output, probably from the same prompt across every bullet, and it shows. The fix is a complete rewrite from your own memory of the work you actually did, not a quick edit. Use the AI rewriter only on individual hardened sentences after you have rebuilt the structure from your own notes.
Resumes use the same five base signals as the essay scorer, but with weighting calibrated for short bullet-driven content. Action-verb cycling and vague-impact phrasing carry the heaviest weight because they are the strongest resume-specific tells. Quantified-specificity detection runs as a positive offset that lifts the score back up when you do the work.
"Spearheaded", "Orchestrated", "Leveraged", "Pioneered", "Championed", "Drove", "Engineered", "Architected" all appearing on the same resume in rotation. AI tools cycle through the same small set of high-flash verbs because they were trained on resume guides that recommend exactly that list. Real candidates use the verb that actually describes the work, often a simpler one (Built, Wrote, Shipped, Reduced, Fixed). The scorer weights a page stacked with rotating flash verbs as a strong tell.
"Resulting in increased efficiency", "Leading to significant improvements", "Contributing to enhanced productivity". Real impact comes with a number. AI tools avoid numbers because they tend to invent the wrong ones, so they default to abstract impact phrasing. The scorer weights impact phrases that carry no number or named outcome heavily on this signal. Replace each instance with the specific result, even if the result is small, such as "by 4%" or "from 11 minutes to 8".
"Proficient in Python, Java, C++, SQL, AWS, Docker, Kubernetes, and Terraform." This comma-separated skills cram is a classic recent-grad resume pattern and one of the patterns ATS classifiers learned to flag earliest, because it carries zero evidence the candidate has actually used any of those tools. The fix is replacing the list with one or two bullets that name a single tool and the specific thing you built with it. Keep the skills cram in a separate Skills section if the format demands it; do not put it inside an experience bullet.
Resumes where every bullet runs 14 to 18 words trip a structural flag because real careers do not produce uniform-length stories. LLMs default to uniform length because they were trained on advice that says bullets should be "consistent and parallel". Real bullets vary: a strong quantified bullet might run 22 words, a clean one-line achievement runs 9. The scorer treats variance in bullet length as a positive signal and uniformity as a negative one.
This signal pulls the score up rather than down. The scorer rewards bullets that name a specific tool, a specific team size, a specific time frame, or a specific percentage or dollar move. Specifics are the cheapest gain on a flagged resume and the single highest-leverage thing to add before re-scanning, because they are exactly what generic AI phrasing leaves out. Turn one round of edits into a quantified-specifics pass and the score usually moves the most on its own.
All three AI rewriter modes are available on every paid plan. The free tier handles two to four resume versions; job seekers tailoring a resume per application usually move to Pro for 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 career cost of an over-AI resume is not usually a dramatic rejection. It is quieter than that: the resume reads like every other AI-written one in the stack, the recruiter moves on, and you never hear why. Two things are working against you, and the score helps with both.
Hiring teams increasingly run resumes through AI-writing checks, and recruiters themselves have read enough generated resumes to recognise the pattern on sight. You do not need to know exactly which tool a given employer uses. The defensive move is the same either way: make the bullets specific enough that no template could have produced them. A flagged, generic bullet is a missed chance to say something only you could say.
The Authenticity Score is a directional pre-flight check, not a mirror of any employer's screening tool. We do not have access to what a given company runs, so we will not pretend the number predicts a specific recruiter decision. What it does do is surface the bullets that read generic to a classifier trained to recognise AI phrasing, which is the same phrasing a busy recruiter glosses over. A higher score means fewer of those bullets remain. The per-bullet colour map, not the number, is what tells you where to spend your editing time.
A resume bullet is a dozen or two words, surrounded by other short bullets. There is nowhere for a generic line to hide. A single cycled action verb at the start of a bullet stands out far more than the same verb buried in the middle of a long paragraph. That is why resumes need a tighter target than essays do, and why the cheapest, highest-leverage edit is almost always swapping a vague line for a quantified one.
A recruiter gives most resumes a few seconds before deciding to read on or move to the next file. Generic AI phrasing is exactly what triggers the move-on, because it reads like work they have already skimmed a dozen times today. These are the three spots where specificity earns you the rest of the read.
The assessment usually gets made on the first bullet under your most recent job title. By the second bullet the frame is set, and the rest of the experience section reads through it. Specific, quantified work in the top bullet is the single highest-leverage edit on the page. The scorer weights action-verb cycling and vague-impact phrasing accordingly, so a quantified opener that names the tool, the team, and the result moves the score more than any other single change.
Spearheaded, Orchestrated, Leveraged, Pioneered all on one page read as a template, to the human and to the classifier alike. Cut them. Use the plain verb that describes the work: Built, Wrote, Shipped, Reduced, Fixed, Trained, Hired. A plain verb followed by a specific result is the rhythm a real career produces and the one generic AI text rarely lands on, so the score and the recruiter response both move when you make the swap.
"Proficient in Python, Java, C++, SQL, AWS, Docker, Kubernetes" inside an experience bullet reads, to a recruiter, like a candidate who has used none of them in production. Move the skills cram to a separate Skills section if you must, then replace the experience bullet with one project that actually used one of those tools. A resume that jumps into the 80s after this edit usually does so because that single bullet was carrying half the generic signal on the page.
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.
Resumes you wrote yourself, including ones where you used ChatGPT to draft bullets from your own notes and then edited them down. The career is yours, the tools are real, the numbers are real. The scorer catches bullets where assistant register leaked into the prose so the submitted resume reads in your own voice and the interview conversation lines up with the page. We score honestly so you can decide what the resume needs.
It is not a tool for fabricating qualifications or pretending you wrote something you did not. The AI rewriter cannot put authentic experience into a bullet about work you did not do. If your resume sounds AI because the underlying experience is borrowed wholesale from a job description, 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 the work you actually did, even if the work feels less impressive than the job description sounds.
The output of a good revision pass should pass a simple test: if the recruiter asked you in an interview to walk through any specific bullet on the resume for two minutes, you should be able to do it confidently. If you cannot, the revision added voice but not substance, and the resume will fail anyway when you reach the screen. The score is a draft check, not a substance check, and we are honest about that limit because the alternative is a candidate who passes the bullet sweep and then stalls on the first behavioural question.
The upstream detector page with the full benchmark methodology and ATS calibration details.
Read the methodology →The sister scorer for cover letters, with template-opener and enthusiasm-cluster calibration.
Open the scorer →Why STEM and ESL writing get flagged at higher rates, and what we calibrate for to keep FPR low.
Read the guide →How we measure precision, recall, and false-positive rate across document types and writing styles.
Read the methodology →The full four-fix rewrite workflow for ChatGPT cover letters with before/after examples.
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, per-bullet highlights, ATS-aware calibration. Free for two to four resume versions per month.
Run the Authenticity Score on the exact thing you're about to send.