Free Tool

How to Use ChatGPT to Rewrite Your Resume (The Right Way)

By John Akande · 9 min read · May 22, 2026

TL;DR

Most ChatGPT-assisted resumes fail because they sound like everyone else using the same prompts
The correct process starts with your raw experience, not a request to "write my resume"
ATS systems filter 75% of resumes before a human sees them — keyword matching is non-negotiable
The final edit is always yours — AI cannot replicate your actual career story accurately

Why most ChatGPT resumes fail

I have reviewed hundreds of resumes over the years. Since 2023, I can spot an AI-assisted resume from the first bullet point. They all sound the same. "Results-driven professional with a proven track record of delivering impactful outcomes." That sentence is in approximately 40% of resumes right now.

The problem is not that people used AI. The problem is that they used it wrong. They asked it to write their resume from scratch. That produces generic output because the AI has no specific knowledge of your actual achievements.

The right approach is different. You supply the substance. AI helps you structure and sharpen it.

Step 1: extract your raw experience first

Work With John

Your site should be your best salesperson. If it is not, that is a fixable problem.

I work with US service businesses and B2B brands to build SEO systems that produce consistent, compounding leads. I will tell you exactly what is broken. No pitch.

Book a free strategy call

Before you open ChatGPT, document your actual experience. For each role in the last 10 years, write answers to these questions: What did I actually do? What changed because of my work? What specific numbers can I attach to my contribution?

This does not need to be polished. It can be rough notes, bullet points, even voice memos transcribed. The goal is to capture the raw material that AI cannot invent but you can supply.

Specific numbers matter most. "Increased sales" tells nobody anything. "Increased inbound lead volume from 12 per month to 38 per month over six months" is specific, verifiable, and compelling. If you do not have exact numbers, use estimates with ranges: "Generated approximately 25-30 qualified leads per month."

Step 2: use the job description as your keyword source

ATS systems — the applicant tracking software most companies use to filter resumes — work by matching keywords from the job description to keywords in your resume. Before you ask AI to help rewrite anything, paste the job description into a Google Doc and highlight every skill, tool, and requirement mentioned more than once.

Those are your must-include terms. Your resume needs to contain them naturally. Not crammed in. Not in a hidden keyword list at the bottom. Woven into your actual experience bullets.

The prompt that actually works

Do not say: "Write me a resume for a marketing manager role."

Do say: "I am applying for this role [paste job description]. Here are my relevant experiences [paste your raw notes]. Rewrite these experience bullets to be specific, achievement-focused, and to naturally include the key terms from the job description. Do not use generic phrases like 'results-driven' or 'proven track record.'"

This prompt gives the AI the specific material it needs to produce output that sounds like you, not like every other AI-assisted resume in the applicant pool.

Step 3: the human review that cannot be skipped

Read every line the AI produced. Check three things. First: is every claim accurate? AI will sometimes infer details you did not provide. Remove or correct anything that is not verifiable. Second: does it sound like you? If you speak plainly and the output sounds formal and corporate, adjust the tone. The resume should represent who you actually are. Third: does every bullet start with a strong verb? "Managed," "built," "reduced," "generated," "led" — not "was responsible for" or "helped with."

Step 4: format for ATS and humans simultaneously

ATS systems strip formatting. Bold, tables, columns, and graphics often disappear or render as garbled text. Use a clean, single-column format. Standard section headings: Experience, Education, Skills. No text boxes. No graphics. Save as a PDF only if the job posting specifically allows PDFs — some ATS systems cannot parse PDFs and will reject them automatically.

The human who eventually reads your resume should find it easy to scan in 10 seconds. Each bullet should communicate one specific achievement. The reader should not have to work to understand your value. If they have to re-read a bullet to understand it, rewrite it.

The one thing AI consistently gets wrong

AI does not know what you are most proud of. It does not know which of your achievements was the result of exceptional work versus standard performance. It cannot distinguish a routine task from a career-defining moment. You have to make that call.

The most compelling resumes I have seen give disproportionate space to 2-3 achievements that genuinely differentiated the candidate. Not a long list of everything they did. A focused narrative of the things that only they could claim.

Stay Sharp

Guides like this, twice a month.

No agency talking points. No keyword stuffing. Just the frameworks I use on paid engagements, free.

No spam. Unsubscribe any time.

Frequently asked questions

Recruiters are increasingly able to identify AI-assisted content that uses common AI phrases and patterns. The way to avoid detection is to ensure the output sounds specific to you and your actual experience. Generic phrases are the tell. If your resume has specific numbers, named projects, concrete outcomes, and a tone that matches your professional communication style, most recruiters will not flag it as AI-generated.

Tailor each application. ATS keyword matching means a resume optimised for one job description will fail ATS filters on a different role with different language. The base content stays the same. The bullets and summary section should be adjusted to match the language of each specific job description. A 20-minute tailoring session per application significantly increases interview rate.

One page for under 10 years of experience. Two pages for 10+ years of relevant experience. Three pages is almost never justified for non-academic roles. The constraint forces you to prioritise your most relevant, most impactful experience. If everything feels equally important, nothing is. Cut anything that does not directly support the case for this specific role.

Yes, with the same approach. Supply specific context: the role, why you are applying, and one specific reason you are well-suited that is not already obvious from your resume. Ask the AI to draft a cover letter that opens with that specific reason, not a generic opener. Cover letters are also heavily pattern-matched by ATS systems and read by humans looking for genuine interest, not boilerplate enthusiasm.

Claiming credit for team achievements without clarifying your role, using inflated titles or responsibilities that references will not confirm, and omitting gaps without explanation when the gaps are visible. AI will reproduce whatever you supply. If your raw experience notes are inaccurate or inflated, the AI output will be too. The accuracy and honesty of the content is always your responsibility.

Address gaps directly in the summary section or a brief note in the experience timeline. A gap spent on freelance work, caregiving, or professional development is not a negative if you name it. Leaving a visible gap with no explanation invites assumptions. "Independent consulting (2024)" or "Career break for family caregiving (2023-2024)" is better than silence. AI can help you frame the gap professionally.

Yes. Use the same approach: supply your specific experience and achievements, reference the role types or searches you want to appear in, and ask the AI to rewrite sections with those in mind. LinkedIn's algorithm favours profiles with complete sections, keyword-rich summaries, and specific achievement language. The same principles that improve a resume improve a LinkedIn profile.

John Akande

SEO specialist and growth operator working with US service businesses and B2B brands. I build search infrastructure that produces compounding leads — not just rankings.

Book a free strategy call More guides →

← Back to all resources