A résumé and cover letter tailored to the listing

Most people have one résumé and send it everywhere. But the recruiter is reading the job listing, not your résumé — and scanning it for words they wrote into the listing themselves. If you spent two years doing “customer support” and the role is looking for someone in “client onboarding,” that's nearly the same thing, just in different language. And the difference between “no reply” and “let's talk” often isn't about what you can actually do — it's about whether it was written so a reader can tell within thirty seconds.

AI can reframe your actual experience into the vocabulary of a specific role and reorder it so the important parts sit in the top third of the page. It must not invent anything in the process — and that rule is what the whole approach stands or falls on. A made-up line on a résumé isn't a clever move: it's the fastest way to make an interviewer stop trusting the rest of it too, and it shows within two follow-up questions at the interview.

This guide walks the whole application from the first read of the listing to the email three days after the interview. The phases are in the order you'd actually do them, and each comes with copy-paste prompts — just fill in the brackets. If this is your first time through, read the whole thing; if your résumé is done and you're heading into an interview, skip straight to phase 6. And one thing up front that overrides everything else: a résumé is a concentrate of personal data, so read the short section on what to strip before you upload it.

A typical scenario

Mark is finishing his master's degree and applying for a junior marketing role. He has one generic résumé: part-time jobs, a semester project, six months running a student club, two years of retail sales at an electronics store. He sent it to twelve postings and got two replies — one rejection and one automated one.

Then he tries a different approach. For one specific listing, he uploads his résumé and the posting text and asks for an analysis: what the listing asks for, which of that his résumé actually covers, and what's missing. It turns out “running a student club” covers exactly three things the listing wants — event planning, sponsor communication, and social media management — except in his résumé it was one line with no detail. The retail job, meanwhile, means customer-facing work and product knowledge, which the listing mentions twice. And the list of gaps is short: he's missing experience with paid advertising and one analytics tool. He doesn't fake them — he prepares an answer for them instead.

The rewritten version has the same facts, a different order, and different vocabulary. The cover letter doesn't retell the résumé — it answers three specific sentences from the listing. He adjusts LinkedIn so it says the same thing as the résumé, since the recruiter will open it second. He has fifteen likely interview questions generated from the listing and rehearses the three toughest out loud. Out of four more applications, he got two interviews. It took him twenty-five minutes per application instead of an hour and a half — plus an extra hour of prep he'd never done before.

Phase 0: safety — what to strip from your résumé before uploading it

This phase takes two minutes and most people skip it. A résumé contains an address, phone number, email, employer names, often a date of birth, sometimes a national ID number or a photo. All of that is personal data, and none of it belongs in a conversation with AI unless it actually has to be there.

The key finding is that the analysis works exactly as well on a résumé with no contact details. The model needs to see what you did — not where you live.

Before you upload anything, do three things. Delete the header with your contact info — name, address, phone, email, date of birth, links to profiles. Think twice about employer names: for large companies it doesn't matter, but for a small company or nonprofit where you're the only person in that role, the name effectively identifies you. Replace it with a description (“a mid-sized e-commerce company, 40 people”). And cut anything that doesn't belong in the analysis — references with colleagues' names and phone numbers, contract numbers, internal project names covered by an NDA.

Then the rule that applies everywhere on this site applies here too: sensitive data belongs only in a paid or business account with contractual data protection, not a free chat. And don't re-upload the finished résumé with contact details back in — add your contact info yourself, in your own editor, at the very end.

Be especially careful if you're job hunting while still employed at your current job. Don't mention anything in the conversation that could reveal internal details about your current employer, and definitely don't use your work account for this.

Phase 1: breaking down the listing

The listing is the only material you have about the role, and it's denser than it looks. Most people read it and turn it into three bullet points. That's a mistake: the listing also carries how the company talks about itself, what it repeats more than once, what it put up top, and what's just boilerplate.

The key distinction that the rest of this guide runs on: what's a requirement, what's a nice-to-have, and what's just filler text.

What they're actually looking for

Upload the whole listing, including the passages about company culture and “what you'll get here.” Don't rewrite it into bullet points first — the parts that look like marketing are usually exactly where the vocabulary the company uses about itself lives, and you'll want that for the cover letter.

Here's the full text of a job listing:

[paste the whole listing, including the sections about the company
and benefits]

Analyze it. Don't write anything about me yet, just about the
listing.

1. What does this role actually involve day to day — describe a
   typical workday the way you picture it from the listing.
2. Split the requirements into three groups, noting for each what
   told you it belongs there:
   - MUST have (without this I don't get hired)
   - WOULD LIKE (a plus, catchable later)
   - FILLER (phrases that don't mean anything)
3. What's repeated more than once in the listing, or mentioned
   right at the start? That's probably what matters most to them.
4. What problem is this hire most likely solving? Why did they open
   this position?
5. What's conspicuously missing from the listing, and what should I
   ask about?
6. What vocabulary does the company use — list 15 words and phrases
   it uses that I should use too.

For points 1 and 4, mark what's your guess, so I don't confuse it
with what's actually stated in the listing.

It returns an analysis that, for the first time, shows the priority of the requirements. Point 4 is the reason this prompt is worth it: “looking for someone to manage social media and reporting” at a small company usually means someone's been doing it on the side and it stopped being sustainable — and that's information you'll use in the letter and at the interview. But treat the guesses with caution: the model is speculating about the company, and point 4 is speculation by design.

Decoding company language

Some phrases in listings mean something other than what they say. “Work in a dynamic environment,” “looking for a partner, not an employee,” “high degree of independence,” “we wear a lot of hats.” It's not always a warning sign, and it's not always just a phrase — but it's worth knowing what to think of it, and what to ask.

Here are some phrases from a listing I don't fully understand or
that seem off to me:

[list the sentences verbatim]

For each, tell me:
- what it most often means in practice
- an optimistic interpretation and a pessimistic one
- one specific question I could ask at the interview to check it,
  phrased so it doesn't sound distrustful

Don't turn this into a list of warnings. I want to understand, not
get scared off.

It returns a translation, and more importantly, questions that sound natural at an interview. The last line of the prompt is there on purpose — without it, models love to turn every phrase into a red flag.

Phase 2: taking stock of your own experience

You can only reframe what actually exists. The most common reason a rewritten résumé doesn't sound much better isn't a bad prompt — it's thin source material. “Ran a student club” is one line. What's behind it: how many people, how long, what exactly you did, what came out of it. You have to pull that out of your own head — the model can only get it out of you.

Unpacking one-line entries

I have this entry on my résumé written as a single sentence:

“[paste the entry, e.g. President of a student club, 2024—2025]”

Interview me so we get something usable out of it. Ask me one
question at a time, in order, and wait for my answer each time.

Ask about:
- what I did repeatedly, specifically (actions, not the title)
- who I worked with and how many people
- what tools and systems I used
- what came out of it, what changed, what's quantifiable
- what was hardest and how I solved it
- what I'd do differently today

When we're done, summarize it into 5—8 bullet points written the
way they could appear on a résumé. Use only what I told you.

The conversation takes ten minutes and is the best-spent time in the whole process. Save the result — you'll reuse it for every future application — and keep adding to it over time, not only when you're job hunting. Watch for one thing: in the final summary, models tend to inflate (“was responsible for” where you said “helped with”). Go through the bullets and put the weaker verbs back where they belong.

Numbers you have and don't realize you have

A concrete number is far stronger on a résumé than an adjective. Most people think they have none — and they're usually wrong.

Here's my experience described in my own words:

[paste bullet points from all positions]

Go through them and, for each, tell me what number or measurable
figure could plausibly be attached to it — and ask me a specific
question that helps me recall it.

Look for: counts (people, orders, events, customers per day),
volumes, frequency (how many times a week/month), duration, scope
of responsibility, budget size, before/after change.

Don't invent any numbers or example numbers. Just ask.
Where I can't think of a number, tell me how to describe it without
one so it doesn't feel empty.

“Don't invent any numbers or example numbers” is a necessary safeguard: models love to offer sample phrasing like “increased revenue by 20%,” and people accidentally paste it straight into their résumé. A number you can't back up and explain doesn't belong on a résumé.

A gap analysis

Only now can you compare the listing to what you actually have. And that second list — what's missing — is just as valuable as the first.

You have the listing analysis from the previous step, and here's my
résumé (no contact details):

[paste your résumé]

Do a three-table comparison:

1. I COVER: requirement from the listing | specifically what from
   my résumé | how strongly (direct experience / related /
   marginal)
2. I PARTIALLY COVER: requirement | what of mine comes closest |
   what I'd need to add for it to fit
3. I DON'T COVER AT ALL: requirement | how big a problem this is |
   catchable before starting, or not

At the end, tell me:
- your estimate of whether it's worth applying, and why
- 3 things from my résumé that are strongest for this role
- 3 things that are irrelevant for this role and should be
  shortened or cut

Don't sugarcoat it. If the match is weak, say so.

It returns a realistic picture. Save the “don't cover at all” column — it's the list of questions you'll prepare for in phase 6. And don't treat a weak overall match as a reason not to apply: for junior roles it's normal to cover half of it, and companies know that. A reason not to apply is when something from the “must have” group is missing.

Phase 3: reframing without inventing

Now comes the writing. And there's one rule you have to put in every prompt from here on, because without it everything else falls apart.

The hard rule

Don't invent. You may rephrase and reorder what's already in my résumé. You may not add any skill, tool, number, or experience that isn't there. If something is missing, list it separately, but don't put it in the résumé.

Without this sentence, the model will add “experience with analytics tools” because it logically fits the role — and you'll find out at the interview. Models don't lie on purpose; they fill in whatever looks like a plausible continuation in context. That's exactly why the ban has to be stated explicitly and repeated at every step that generates text.

Rewriting entries in the role's language

Rewrite my résumé for this specific role.

RULES that override everything else:
- Don't invent. You may only rephrase and reorder what's already in
  my résumé or in my notes below.
- You may not add any skill, tool, number, or experience that isn't
  there.
- Don't inflate verbs: don't turn “helped with” into “led,” don't
  turn “participated in” into “ran.”
- Where something would be worth adding but I don't have it, put it
  in a “missing” list at the end — don't put it in the résumé.

What to do:
- use the listing's vocabulary wherever it describes the same thing
  I do
- start every bullet with a verb and note what came out of it
- expand the bullets for relevant positions, shrink irrelevant ones
  to one line
- at most 5 bullets per role, 2 for older positions

Listing: [paste]
My résumé: [paste]
My notes on each position: [paste the output from phase 2]

At the end, give a table: original wording | new wording | why you
changed it. I want to see every single change.

That final paragraph is the most important control tool. The change table shows you exactly where the model shifted meaning — and it will happen on two or three items almost every time. Go through it line by line and revert anything that's been shifted.

Order matters more than phrasing

The most valuable change is often not the rewording but what's at the top. People read the top third of the page carefully and skim the rest; the first screening pass is usually about thirty seconds per résumé.

Here's my rewritten résumé and the listing analysis.

Reorder it so the first 15 lines cover what's most relevant to this
role.

- propose an order for the sections (experience / education /
  projects / skills / languages) and justify it for this specific
  listing
- within sections, order entries by relevance, not just by date —
  and where that breaks chronology, tell me how to handle it
- propose a short 2—3 line summary right at the top: who I am, what
  I can do relevant to this role, what I'm looking for
- tell me what fits on one page and what has to go

Write the summary at the top in three variants so I can choose.
None of them may contain anything that isn't in my résumé.

It returns a reordered version and three summary variants. The summary is the one part of the résumé almost everyone reads — pick the variant you can say out loud without flinching.

A truthfulness audit

The last step of the phase, and not one to skip. Go through the result and, for every sentence, ask yourself: is this true, and could I expand on it in an interview for two minutes? Cut what doesn't pass.

Here's the final version of my résumé:

[paste]

Play the role of a recruiter who's brought this résumé into an
interview and wants to check there's substance behind it.

For each bullet, give me:
- one follow-up question they'd ask
- what they'd expect to hear in the answer to be convinced
- how they'd tell it was inflated

Separately flag any bullets that sound stronger than what's
probably actually behind them — the ones where I might stumble on
a follow-up question.

Don't judge whether it's true — only I know that. Just ask.

It returns a list of questions about your own résumé and flags anything that sounds inflated. This is where the decision gets made: for anything you can't expand on, either dig up the backing detail from memory or cut it from the résumé. The site's core rule applies here: AI proposes, the person approves — and here you're approving claims about yourself.

Phase 4: ATS and keywords

A large share of applications first pass through a system that processes résumés mechanically — stores them, extracts data from them, and makes them searchable. There's a lot of myth around these systems, including the idea that “a robot rejects you.” The more realistic picture is simpler: a résumé that a machine reads poorly is harder to find and harder to search, and a recruiter searches using words from their own listing. That's the whole logic, and all you need to do is satisfy it.

Keywords from the listing, not from anywhere else

The source of your keywords is that specific listing. Not a “most in-demand skills of the year” list, not words from other listings for a similar role.

Pull the keywords a recruiter might search for out of this listing:

[paste the listing]

Split them into:
- job titles and role names
- tools, systems, and technologies
- technical terms and methods
- soft skills, named the way the listing names them
- abbreviations and their spelled-out forms (both, since people
  search for either)

Then compare against my résumé:

[paste your résumé]

Table: keyword | is it in my résumé? | if yes, where | if no, do I
actually have this experience, just under a different name? (say
how)

The last column is a question for me, not a statement. Don't add
words to the résumé — just show me where I describe the same thing
differently.

It returns an overview showing where you just need to align terminology. A key boundary: renaming what you actually do is fine; adding a word for a skill you don't have isn't. And avoid the old trick of hidden white-on-white text stuffed with keywords — it's detectable and it ends the application right there.

A format that reads cleanly by machine

Check the structure of my résumé from a machine-processing
standpoint. Here's its content exactly as I copied it out of the
finished PDF:

[paste text copied out of the finished PDF, not the original file]

Check:
1. Whether the text copied out fully and in the right order —
   flag anything scrambled or missing as something to fix.
2. Whether section headers are standard and clear (Experience,
   Education, Skills, Languages) — flag unusual ones.
3. Whether dates for each position are in a consistent format.
4. Whether contact info is readable as text, not as an image.
5. What's in a table, a multi-column layout, or a graphic element
   that could fall apart.

For every issue, give a concrete fix. No generic résumé design
advice.

The trick is pasting text copied out of the finished PDF — exactly as a machine would see it. If columns get scrambled or half the details disappear when you copy it, you have your answer immediately, with no tool required. Graphic résumés with sidebars and icons look nice and break the most often.

Phase 5: a cover letter that doesn't repeat the résumé

The most common cover letter mistake: it retells the résumé. The recruiter has it right next to them and reads the same thing twice. The letter has to answer the question the résumé can't — why you, specifically, and why this role, specifically.

Write the letter as step three, not step one. Only once the résumé is settled, since the letter builds on it.

A structure derived from the listing

Write me a skeleton cover letter for this role.

Inputs:
- listing: [paste]
- my final résumé: [paste]
- why this role interests me, in my own words: [write 3—5
  sentences, rough is fine]
- what I know about the company: [paste what you've found out]

Rules:
- The letter must NOT retell the résumé. Pick three specific things
  from the listing and, for each, say how I cover it — with one
  concrete example that isn't spelled out in the résumé.
- Don't invent anything, including the reasons the company
  interests me. Use only what I wrote.
- At most half a page, 4 paragraphs.
- No stock phrases like “I read your listing with great interest,”
  “I'm a team player,” “I love learning new things.”
- Last paragraph: what I specifically offer in the first three
  months, stated soberly, with no promises I can't keep.

First give me just a 4-point outline so I can approve it.
The full text after that.

The outline first matters: fixing the direction in four bullet points takes a minute; fixing a finished letter is a rewrite. Once the outline fits, let it draft the text.

Rewriting it in your own voice

Text from the model is a rough draft. The technique that works: read the letter, close it, and rewrite it from scratch in your own words. Don't edit sentences — write from memory, with the outline beside you. Anything you can't remember well enough to write yourself probably doesn't belong there.

Then comes a check for any leftover generic tone.

Go through this cover letter and flag any passages that sound like
generated text:

[paste the letter]

Look for:
- phrases that would fit any role at any company
- unsupported superlatives (“a major contribution,” “an exceptional
  opportunity”)
- sentences that don't actually claim anything (“I believe I'd be
  an asset”)
- three synonyms in a row instead of one precise word
- paragraphs that just retell the résumé

Only FLAG them and briefly say why for each. Don't rewrite or
suggest replacements — I'll rewrite it myself.

At the end, tell me which two sentences in the letter are the most
specific, so I know what to build around.

The ban on rewriting is there on purpose: if you let the model “fix” the letter, you'd just trade one set of generic phrases for another. Flagging the most specific sentences, on the other hand, gives you something to build the rest of the letter around.

Phase 6: LinkedIn consistent with your résumé

The recruiter almost always opens your profile, usually right after the résumé. A mismatch between the résumé and the profile — different dates, different job titles, experience that only shows up in one place — looks bad and is awkward to explain. But the profile shouldn't be a copy of the résumé: a résumé is written for one role, a profile for all of them.

Here's my final résumé and here's the current text of my LinkedIn
profile:

Résumé: [paste]
Profile: [paste the headline, About section, and position
descriptions]

Do two things:

1. Find every inconsistency between the résumé and the profile:
   - different dates for the same position
   - different role titles
   - experience that's only in one of the two documents
   - different phrasing for the same thing
   List them in a table: résumé says | profile says | what to do
   about it.

2. Propose edits to the profile so it doesn't contradict the résumé
   but stays more general — the profile is also read by someone
   hiring for a different role.
   - 3 headline variants
   - a 4—6 sentence About section, first person, no stock phrases
   - 3 bullets per position on what I actually did there

Don't add anything that isn't in the résumé. Where the résumé is
silent and the profile claims something, ask me which one is true.

The last line catches a common situation: your profile has text from years ago that you've since outgrown or that was never quite accurate. Resolve the conflict in favor of the truth, not whichever sounds better. And remember a public profile is public — whatever you write there, your current employer can see it too.

Phase 7: interview prep from the listing

The listing is the best prep material there is: the interview is built from it, because whoever wrote it is the one filling the role. This phase is also the one part of the whole process most people skip entirely — and it matters more than the wording of the résumé.

Likely questions

Prep me for the interview for this role.

Listing: [paste]
My résumé, as sent: [paste]
Gap analysis from earlier: [paste the “don't cover” list]

Generate 15 questions I could realistically be asked, split into:
- technical, directly from the listing's requirements (7)
- about my résumé — mainly places that invite a follow-up (4)
- about the gaps, i.e. what the listing wants that isn't on my
  résumé (4)

For each question, give me:
- why they're asking, what they're trying to find out
- a skeleton for a good answer in 3 points, built ONLY on what's in
  my résumé
- what would make the answer fall flat

Phrase the questions the way a person would actually ask them, not
as bullet-point requirements. Don't write full answers for me —
I want a skeleton, I'll write the text myself.

It returns an hour's worth of prep material. Say the answers out loud — the difference between “I could explain that” and actually explaining it only shows up once you have to turn it into sentences. For harder practice, follow up with rehearsing a tough conversation with AI playing the other side.

Answers for what you don't know

The most uncomfortable questions are the ones about your gaps. A bad answer is faking it; an even worse one is apologizing. There's a third way that works: admit it, show the closest analogy, and state a plan.

The listing wants [skill / tool / experience] that I don't have.

My actual situation: [describe honestly — e.g. I've seen it done by
a colleague, I did something similar in a different tool, I know
the principle from another area, I know nothing about it].

Help me prepare an honest answer:
- how to admit it in one sentence, with no apologizing or dodging
- which of the things I actually can do comes closest, and why
- what specifically I can do to catch up, and in what timeframe
- how long the answer should be so it doesn't turn into a ten-
  minute topic

Don't offer phrasing that claims more than what I wrote. If my
answer is “I know nothing about it,” don't paper over that.

It returns an answer you can say without flinching. The last paragraph guards against the model's tendency to turn “I don't have this” into “I have basic familiarity” — that's the start of a problem, not a solution to one.

Questions you ask them

The end of the interview, when it's your turn to ask, often gets shortchanged. It's actually the one part where you find out whether you want to work there.

From this listing and what I know about the company, prepare
8 questions for me to ask at the end of the interview.

Listing: [paste]
What I know about the company: [paste]
What matters to me in a job: [write 3 things]

Conditions:
- no questions whose answer is already in the listing
- for each, note what the answer would tell me and what a red-flag
  answer would look like
- 3 questions about the day-to-day and expectations in the first
  few months
- 2 about what collaboration looks like and who my closest colleague
  would be
- 2 about why the role is open and what's expected from it
- 1 about the next steps in the process and by when they'll be
  in touch

Order them by which are most important to get to if only two make
it in.

The question about red-flag answers is the valuable one: you know in advance what answer should make you cautious. And the last point — when and how they'll follow up — also sets up the next phase.

Phase 8: the follow-up after the interview

A short email the day after an interview is a cheap move with an asymmetric payoff: it offends no one, it sometimes helps, and it puts you back in front of the decision-maker at the right moment. There's one rule — it has to add something, not just say thanks.

Write me a short email to send the day after my interview.

When the interview was: [date]
Who I spoke with: [name and role]
What we mostly talked about: [2—3 topics]
What I answered poorly or incompletely: [describe]
What I promised to send: [if anything]

Structure:
- a one-sentence thank-you, no gushing
- one specific thing from the conversation that stuck with me or
  that I thought of afterward — that's the core of the email
- a fuller answer to the thing I fumbled, in 2—3 sentences
- anything I'm attaching, if I promised something
- a close: I offer to send more, I ask about the decision timeline

At most 150 words, no first names unless we were on those terms,
address as [Mr. / Ms. Last name].
No pushiness, no repeating what I already said at the interview.

It returns a draft you should rewrite in your own words and send yourself — sending is always on the human, see the rule AI proposes, the person approves. One more thing to check: names, titles, and project names from the conversation. Models sometimes tweak these while writing, and a typo in the recruiter's name is a needless own goal.

Once the timeline they gave you for a decision passes, send one polite check-in and then wait. And if you get a rejection, it's worth replying with a short thank-you and a request for feedback — sometimes you get it, and it's the cheapest information available about what to change next time. Anyone applying to multiple places at once will appreciate a follow-up tracker so nothing falls through the cracks.

Common mistakes

• Letting the model invent skills. Without an explicit ban, it will add a tool or number that logically fits the role. It shows within two follow-up questions at the interview, and it undermines the parts that were true too.
• Asking for a finished résumé without the analysis first. Skip the listing breakdown and the inventory of your own experience, and you get a document that's reworded but just as generic. The valuable part isn't new text — it's new ordering and knowing what you actually cover.
• A cover letter that retells the résumé. The recruiter has both side by side. A letter that adds nothing new is a wasted page.
• A mismatch between the résumé and LinkedIn. Different dates, different role titles, experience that only shows up in one place. The profile opens right after the résumé, and a mismatch is awkward to explain.
• Uploading a résumé with contact details and a national ID number into a free chat. The analysis works exactly as well without them. Personal data belongs only in a paid or business account with contractual data protection.
• Stuffing the résumé with keywords “for the ATS.” Lists of terms with no backing experience, and hidden white text, are detectable and look worse than a missing skill.
• Rewriting the résumé and skipping interview prep. The text gets you to the interview; you're the one who has to defend it. Fifteen questions built from the listing is the highest-return hour in the entire process.

The best tools

• Claude — reads a résumé in PDF and the listing, and handles the whole process in one conversation, from analysis through reframing to interview prep; it can also pull text out of a photo or scan of an older résumé.
• Projects (persistent context) — upload your experience, numbers, and notes once, and for every new application you just paste in the listing. See projects and persistent context.
• A text editor of your choice — do the layout in your own document and add contact info only there; take text from AI, not formatting.
• Notes with your own examples — keep collecting specific numbers and results from your work over time. You can only reframe what you've written down, and you won't remember it after a year.
• A second model as critic — have a different AI review your finished résumé and letter than the one you wrote them with; fresh eyes catch phrases a “co-author” overlooks. The approach is in the tip AI as opponent.

What you get out of it

• Time: an hour and a half for a careful application shrinks to roughly a third of that. That's the difference between “I'll send three careful applications” and “I'll send ten.” And interview prep, which used to not happen at all, fits into a single hour.
• Money: indirectly, but tangibly — a shorter job search and being better prepared for the expected-salary question, which you now think through in advance instead of on the spot.
• Peace of mind: you know your gaps ahead of time, so a question about what you can't do doesn't catch you off guard at the interview. And for the fifteen most likely questions, you already have an answer you've said out loud.
• Quality: the same facts, described in the role's own language, get past the first screen, where word matches often decide. The résumé, letter, and LinkedIn profile all come from the same analysis and don't contradict each other — and everything in them is something you can actually explain.

Pro tip

Set up one permanent document you can call a “stockpile.” It's not a résumé — it's everything you've ever done, written out in detail: actions, numbers, tools, situations you solved, sentences that worked at an interview. You never send it anywhere. Every application is then a selection from it, not writing from scratch, and after a year it holds things you'd never have remembered on your own. Add to it continuously, especially right after something goes well — not only when you're job hunting, because by then you won't remember anything.

And watch your data: a résumé is a concentrate of personal information — address, phone, employer names, sometimes date of birth. Use a paid or business account with contractual data protection, not a free chat, and strip out whatever isn't needed for the analysis before you upload it. The closing rule of this whole guide is one sentence: rephrase, yes — add, no. Everything on the résumé, letter, and profile has to be something you could expand on from memory in two minutes at an interview — and whatever doesn't pass that test doesn't belong there, no matter how good it sounds.