Can you tailor a resume to a job description with a free chat model? Yes, and it works in ChatGPT, Claude, Gemini or any current model. The catch is the prompt most people type, "Tailor my resume to this job description." It borrows the posting's words and puts claims in your summary that your experience never made, and every one of those is a question you will be asked in a screening call.
This guide gives you the full loop instead: nine steps and fourteen copyable prompts. Seven of the steps select from what is true about you. Eight of the prompts check the draft rather than write it, and they are the part that keeps a fluent draft from claiming more than you did.
This guide is published by JobShifu, which sells a tool that automates the loop. The loop is given away complete and works without it. Every outside number is sourced and dated at the end.
What you are tailoring for
Most free guides aim at a keyword match score so that the applicant tracking system does not reject you. That target is mostly fiction. Jobscan, the largest vendor in ATS optimization, says an ATS rarely rejects a candidate automatically [1], and when Enhancv interviewed 25 US recruiters in late 2025, 2 of them had configured any content based automatic rejection [2]. The longer story is on does an ATS reject your resume.
What is in your way is a person with a pile. Greenhouse's data across more than 640 million applications shows applications per open role rising from 116 in 2022 to 244 in 2025, while recruiters per organisation fell from 10.43 to 4.62 [3]. So:
- The top third of page one has to prove you fit this job, because that is what gets read.
- Every line has to survive being asked about in the screening call, because that is where an invented line costs you.
- A keyword counts as evidence inside a bullet, not as a token in a skills list, because a person is reading, not a counter.
The loop, in nine steps
Step 1. Build the master resume you will never send
A model can only select from what you give it, so start with one document holding everything. Yale's career office describes the master version as ten years of experience, education, skills, training, awards, publications, coursework, volunteer work, memberships and presentations, from which you derive a one or two page resume for each application [4]. Length does not matter here; detail does. Numbers, tool names, team sizes, timeframes, the small projects you stopped mentioning.
You are helping me build a MASTER resume. This is an internal document
I will never send to an employer, so length is not a constraint and
completeness is the only goal.
Below is my current resume. For each role in it:
1. List what the bullet points tell you I did.
2. List what a bullet like this usually leaves out: the scale, the
tools, the people involved, the timeframe, the outcome, and what
went wrong.
3. Ask me up to 5 specific questions per role whose answers would turn
a vague bullet into a specific one. Ask about numbers I would know
without looking them up.
Do not write any resume text yet. Do not invent anything. Ask the
questions and wait for my answers.
RESUME:
[paste your current resume as plain text]
Answer in plain language, then ask it to file each answer under the right role, verbatim. Save the result somewhere you can paste from, and add to it every few months while the numbers are still in your head.
Step 2. Find a job worth the effort
No prompt. Pick one posting you would genuinely take, and check how old it is first: a role open for six weeks has already collected most of its applicants.
Step 3. Decode the posting before you touch your resume
A job description is not a bag of keywords. It has a few things that will get you rejected if you lack them, a longer optional list, and a house language. Separating them tells you what the top third of your resume has to prove.
Read the job description below and produce four lists. Quote the
posting's own words. Do not paraphrase into generic skill names.
1. MUST HAVE. Requirements phrased as required, minimum, or essential,
plus anything stated first or repeated more than once.
2. NICE TO HAVE. Requirements phrased as preferred, bonus, or a plus.
3. HOUSE LANGUAGE. The 5 to 8 phrases this company uses repeatedly to
describe the work or itself. Include the exact phrasing, even where
it is jargon.
4. HIDDEN REQUIREMENTS. What the posting implies but does not state:
the seniority really being asked for, the size of team or system,
and the problem they are most likely hiring to solve.
For each item in list 1, say whether it is a hard gate (a licence, a
clearance, work authorisation, a specific degree) or a soft gate
(years of experience, familiarity with a tool).
JOB DESCRIPTION:
[paste the full posting]
Step 4. Run the gap analysis, against the master
Go straight from posting to rewrite and the model cannot tell "did this and did not mention it" from "never did this". It papers over both the same way. A gap analysis against your master keeps the two apart.
Compare my MASTER RESUME to the requirements list below. For every
requirement, output one row:
REQUIREMENT | VERDICT | EVIDENCE
VERDICT is exactly one of:
- COVERED. My master resume contains direct evidence. Quote the exact
line.
- PARTIAL. There is adjacent or weaker evidence. Quote it and say
precisely what is missing from it.
- NOT COVERED. There is nothing in my master resume that supports
this.
Rules:
- Never mark something COVERED on the strength of a job title alone.
- Never mark something COVERED because a related tool appears. Name
the gap.
- If you are unsure, use PARTIAL and say why.
- Do not suggest any rewrite yet.
Then, separately, list every requirement marked PARTIAL or NOT COVERED
that a person in my field plausibly HAS done but would not think to
write down. Phrase each as a question to me.
REQUIREMENTS:
[paste the must have and nice to have lists from Prompt 2]
MASTER RESUME:
[paste your master resume]
The questions at the end are the valuable part. They find work you did and never wrote down, which is what Step 5 saves.
Step 5. Write what you find back into the master, not into this application
Some of what the gap analysis turns up you have genuinely done and never wrote down. Put it in the master, where every future job can use it, not in this one tailored copy.
Below are my answers to the questions you asked about gaps. For each
answer, write ONE master resume entry:
- Which role or project it belongs under.
- One sentence in plain past tense, using my own words and numbers. No
adjectives I did not use. No verbs stronger than what I described.
- The date or period, if I gave one.
- A note of what job description surfaced it, so I know where it came
from.
If an answer is too vague to become a specific entry, say so and ask
me one follow up question instead of writing a weak entry.
Output only the entries. I will paste them into my master resume
myself.
MY ANSWERS:
[paste your answers]
This is the only step that compounds, and the first one everybody drops.
Step 6. Decide whether to apply at all
Tailoring properly costs real time. Spending it on a role you were never going to get is the most expensive mistake in the loop, and it feels like effort.
Using the gap analysis, give me a go or no go recommendation.
Structure it as:
1. HARD GATES. Any must have I marked NOT COVERED that is a hard gate
(licence, clearance, work authorisation, specific degree). If there
is even one, say so plainly and recommend no go.
2. COVERAGE. How many must haves are COVERED, PARTIAL, and NOT
COVERED. Give the counts, not a percentage.
3. THE WEAKEST LINK. The single requirement most likely to end this
application, and whether anything in my master resume can address
it.
4. RECOMMENDATION. Go, go with reservations, or no go, in one
sentence.
Do not be encouraging. I would rather skip a job than waste an hour on
it. Job descriptions are partly aspirational, so do not recommend no
go purely because some nice to haves are missing.
The call is still yours. The prompt makes the trade explicit before you spend the time.
Step 7. Tailor, by selecting rather than by writing
Now the rewrite. You are selecting and reordering true things, not generating new ones. A model asked to "make my resume fit this job" fills gaps, because filling gaps is what it is for. The hard rules below are what stop it.
Produce a tailored version of my resume for the job below.
HARD RULES:
- Use ONLY content that exists in my master resume. If something would
improve the fit but is not in my master resume, do not write it.
List it separately under "NOT WRITTEN, NOT IN YOUR EVIDENCE".
- Do not add, change, or round any number that is not in my master
resume.
- Do not upgrade a verb. If I wrote "supported", do not write "led",
"owned", "drove", "spearheaded" or "architected".
- Keep every bullet under the employer it actually happened at.
WHAT TO DO:
- Select the most relevant content and cut the rest. Cutting is the
main tool.
- Reorder so that the evidence for this job's must haves appears in
the TOP THIRD of page one. Assume the reader stops there.
- Use the posting's own house language where it truthfully describes
what I did. Where my wording and theirs differ for the same thing,
use theirs.
- Put each keyword inside a bullet that shows the outcome, not only in
the skills list. A listed skill is a claim; a demonstrated one is
evidence.
- If my job title differs from the target title but the work overlaps,
do not change my title. Add a headline at the top that bridges them,
in the form "[My real title] with [target area] experience".
- Target [1 or 2] pages.
OUTPUT:
1. The tailored resume in plain text.
2. A CHANGE LOG: for every line you changed or added, the original
line from my master resume it came from, quoted.
3. The "NOT WRITTEN" list.
MASTER RESUME:
[paste]
JOB DESCRIPTION AND REQUIREMENTS:
[paste]
Step 8. Run the eight checks, one prompt each
A tailored draft fails in eight different ways, with different causes. Ask one prompt to find all eight and it finds the most obvious, announces the resume is strong, and stops. One check per prompt is slower, and it is the version that works.
What each check catches:
- Provenance: a line with nothing in your master behind it.
- Scope: a true fact made bigger, with more ownership, reach or authority than you had.
- Entailment: a tool, outcome or duty inside a line that its source never mentions.
- Jagged metrics: a number with no source, a rounded-up number, or a duration that contradicts the role's dates.
- Role integrity: work filed under an employer where it did not happen.
- AI tells: inflated verbs, filler and borrowed phrases that do not sound like you.
- Title seniority: a headline, summary or title claiming a level your evidence does not support.
- Positioning: must-have evidence sitting below the top third, where the reader may never reach it.
Run these against the tailored draft and its change log.
For every line in the tailored resume, quote the text in my master
resume that supports it. If you cannot quote anything, mark the line
NO SOURCE.
Judge only whether the evidence is in the document. Do not reason
about whether the claim is plausible for someone in my field.
List the NO SOURCE lines at the end. Those are the lines to delete.
For each tailored line, compare the size of the claim to the size in
the evidence it cites. Flag any line implying more ownership, more
reach, more duration or more authority than its source supports.
Show each flagged line beside its source. If nothing is flagged, say
so and stop. Do not find something to justify the exercise.
For each tailored line, list the substantive elements in it: each tool
named, each outcome claimed, each responsibility described.
For each, say YES or NO on whether it appears in the cited source
evidence, quoting the source for every YES. Flag any line containing a
NO.
List every number in the tailored resume and quote the master resume
text it comes from.
Flag any number with no source, any number that has been rounded or
scaled up, and any duration that contradicts the dates on the role it
sits under.
For each bullet in the experience section, check that the work
described happened at the employer it is filed under.
Flag any bullet whose supporting evidence belongs to a different role,
naming both employers.
Flag every phrase that reads as machine written rather than as mine:
inflated verbs, filler adjectives, and empty constructions like
"responsible for" or "played a key role in".
Propose a plain replacement for each, using my own vocabulary from the
master resume. If the plain version says nothing, say the line should
be cut.
Compare the seniority implied by my headline, summary and job titles
to the evidence in my master resume.
Flag anything claiming a level the evidence does not support, and flag
any job title that has been altered from what my master resume says.
Bridging a title with a headline is fine. Changing a title is not.
Assume the reader stops at the end of the top third of page one.
List which of this job's must have requirements have supporting
evidence inside that top third, and which have evidence only below it.
For the second group, say which weaker line above could be swapped
out.
Do not add anything. This is a reordering problem, not a writing
problem.
On our sample resume, the one-line "tailor my resume" draft said it had only reordered, yet carried four claims with no basis in the master; provenance alone caught three, and scope caught all four. The full transcripts are published [5].
Before you send it, read the whole thing aloud once. Every check above runs against the document. The read aloud runs against you, and it catches the line you cannot talk about for two minutes in a screening call. That screen, not a detector, is where a model's help shows: the longer case is in will recruiters know I used AI on my resume.
Step 9. Format it, name it, log it
Three things no chat model does for you.
The document. Single column, ordinary headings like Experience and Education, no text boxes, icons, tables or header and footer content. Parsers mangle multi-column layouts, and a garbled job title drops you out of searches.
The filename. Name first, then the role: `Jane-Okafor-Data-Analyst-Resume.pdf`, never `resume-final-v3.pdf`, so the recruiter can find it again. Leave your name out only where applications are anonymised.
The log. Company, role, date, the exact file you sent and the posting URL, so you know which version of you they read when someone calls three weeks later.
Where this loop breaks
Everything above works. The problem is the sixth job, and the twentieth: fourteen prompts and six judgement calls per application, and none of it carries forward. Step 5, the only step that makes the next application easier, is the first one dropped. The checks come next, because they show nothing when they pass, and the draft they would have caught reads well.
If you would rather not run fourteen prompts per job, JobShifu runs the same nine steps for you. Your master resume becomes your profile, and each gap you confirm is added to it, so the twentieth application starts from more evidence than the first. Each change arrives as a card you apply or decline, and the checks run on every build: a line that cites nothing in your profile, or carries a posting term found nowhere in your evidence, stops the resume from building (how the Calibration Engine works). You still pick the job and approve each change. The free tier includes two tailored resumes a day; the rest is on pricing.
The bottom line
A bare "tailor my resume to this job" prompt borrows the posting's language and claims things your resume never said, while telling you it only reordered. So the checks are not optional: if you shorten the loop, shorten steps 1 to 7 and keep step 8. Tailor by selecting true things from a master resume, write every new fact back into that master, and read the result aloud before you send it.
How the sample run worked
The resume is a fictional senior backend engineer with Python, Go and Kafka but no Java or Scala. The posting is a fictional Staff Software Engineer role written to leave real gaps: Apache Flink, production Java or Scala, exactly-once guarantees and PCI DSS or SOC 2. On 13 November 2026 we ran it twice in Claude Sonnet 5.5, once through the guided prompts and once from the one-line request, each followed by the eight checks. Prompts 1 and 4 were not run, because both wait for answers only the real person has. One resume, one posting, one run each: this shows what each check is for, not how often a model slips. Every message and reply is in the data file [5].
Common questions
Is it dishonest to tailor a resume?
No, and the distinction is the whole point of the eight checks. Selecting which true things to show a particular employer, and describing them in language they use, is what every application has always been. Adding things you did not do is different in kind, not in degree. The checks exist to keep the line visible when a model is generating fluent text on your behalf.
Can I just use one big prompt instead of fourteen?
You can, and the sample run shows what that looks like: a draft that described itself as only reordered, with unsupported claims in its summary and skills block. If you shorten anything, shorten steps 1 to 7 and keep the checks.
Which model should I use?
Any current frontier model handles these prompts; the sample run used Claude Sonnet 5.5. Model choice matters far less than whether you run the checks, because any model asked to fit a posting will borrow its words unless something checks afterwards. If you use Claude, using Claude to tailor a resume covers which model to pick and how to set up a Project for a job search.
Do I have to rewrite my resume for every single job?
No. Steps 3 to 6 are cheap and tell you whether step 7 is worth doing at all. For a weak fit, run the gap analysis, write anything new back into your master, and move on. A no go from Step 6 is the kind of answer that saves an evening.
Sources
- Jobscan, "What Is an Applicant Tracking System (ATS)? The Complete 2026 Guide", 10 April 2026. jobscan.co
- Enhancv, "Does the ATS Reject Your Resume? 25 Recruiters Explain What Really Happens". Interviews conducted September to October 2025. enhancv.com
- Greenhouse, Benchmark Report, March 2026, North America. Applications per open role and recruiting team size, 2022 to 2025, from more than 640 million applications across over 6,000 companies. greenhouse.com
- Yale Center for Business and the Environment, Career Planning and Development, "A note about resume writing from CPD", 1 August 2024. careers.environment.yale.edu
- JobShifu, the prompts in this guide run on a fictional test resume and a fictional posting, 13 November 2026. Claude Sonnet 5.5, one conversation per run, every message and reply verbatim: tailor-prompts-run-2026-11-13.json, CC BY 4.0.