Rewrite weak resume bullets inside Google Docs with Gemini (then fix what it made up)
- Posted
- by Oluwaniyi Raji (Android Police)
- Last checked
- Method:
- How we verify
Evidence: Article or interviewA newsletter, journalist or interview account of what happened.
PartialThe source says it only partly worked, or had a significant problem a person had to deal with.
What went wrong: The first draft inflated his experience and included made-up details; it needed a 30-minute human editing pass.
Outcome
Android Police's Oluwaniyi Raji highlighted copied-job-description bullets in his resume and asked Gemini in Google Docs to rewrite them with action verbs and metric-led outcomes. The first output looked like it belonged to someone two levels above him, partly because Gemini made things up; generating took about 10 minutes and his own editing pass about 30 minutes before he had a resume he could submit to a recruiter.
Agent
Prompt Recreated prompt
The source didn't share its exact prompt, so we wrote this from what it describes.
Run this task now, exactly as written below. Everything you need is here, so start straight away and only stop if something required is missing or a rule below tells you to. Goal: Rewrite the weak bullet points in my resume so they show what I actually achieved, without inventing anything. Fill in before running: - The resume section to rewrite: [PASTE OR HIGHLIGHT] - The job I'm applying for: [JOB TITLE / POSTING] - Real numbers I can stand behind: [e.g. articles per month, team size] - Tone: [plain / confident] Rules: - Start each bullet with an action verb and lead with a real outcome. - Only use numbers and facts I gave you; where a metric would help but I gave none, write [ADD NUMBER] instead of guessing. - Don't copy phrases straight from the job posting. - Keep my level of seniority accurate. - Check facts that can change (prices, opening hours, dates, availability, rules) against the official source, and tell me anything you couldn't verify. Output: The rewritten bullets, with a list of every placeholder I need to fill in. You'll know it worked when: every claim in the new bullets is something I could explain in an interview.
Try this in:
This prompt has blanks to fill in, like [PASTE OR HIGHLIGHT]. We'll copy it instead of filling it in, so you can edit it before you send.
Opens in a new tab. We don't see what you send.
These links are only a shortcut. We're not affiliated with OpenAI, Google or xAI, and your results may not match the source.
Optional stronger version
Our rewrite with extra checks. The poster didn't test it.
Run this task now, exactly as written below. Everything you need is here, so start straight away and only stop if something required is missing or a rule below tells you to. Goal: Rewrite the weak bullet points in my resume so they show what I actually achieved, without inventing anything. Fill in before running: - The resume section to rewrite: [PASTE OR HIGHLIGHT] - The job I'm applying for: [JOB TITLE / POSTING] - Real numbers I can stand behind: [e.g. articles per month, team size] - Tone: [plain / confident] Rules: - Start each bullet with an action verb and lead with a real outcome. - Only use numbers and facts I gave you; where a metric would help but I gave none, write [ADD NUMBER] instead of guessing. - Don't copy phrases straight from the job posting. - Keep my level of seniority accurate. - Check facts that can change (prices, opening hours, dates, availability, rules) against the official source, and tell me anything you couldn't verify. - After rewriting, list any bullet that sounds more senior than my real role so I can tone it down. Output: The rewritten bullets, with a list of every placeholder I need to fill in. You'll know it worked when: every claim in the new bullets is something I could explain in an interview. Before you finish: re-read my goal and constraints, check your answer against each one, and list anything you assumed or couldn't confirm.
Source
https://www.androidpolice.com/gemini-rewrote-my-resume-look-like-a-professional-on-paper/
Related cases
- Rewrite a resume from three reviewers' points of view with GrokRecreated promptEvidence: Described by poster
Andrew Donato uploaded his own draft resume so Grok 3 could match his voice, then asked it to critique the resume as a fast-screening in-house recruiter, an outsourced recruiter sourcing a senior sales leadership role, and a CRO. At each step he asked how likely that reader was to reach out and tweaked toward a 9/10, then had Grok merge the feedback in his original tone. He says the two-page result has already gotten him a few responses.
Grok · Personal · Source date:
- Track 186 applications, find missing keywords and review interview notes with Claude to land an offerEvidence: Article or interview
Margareth Felicia Gono, an international student who needed a visa, started job hunting scattershot. Gono built an application tracker with Claude, had it pull the main skills and keywords from each job description and compare them with the résumé, and used it as a career coach, which led to three résumés for analytics, sales and marketing, and consulting. Where interviewers allowed recording, Gono ran sentiment analysis on the notes to see where Gono hesitated or used filler words. The tracker showed 186 applications, 44 cold outreaches, 19 interviews, six take-home assignments, three final rounds and one offer, as a senior associate at DoorDash.
Claude · Personal · Source date:
- Sort 204 unread emails into action labels with ChatGPT, approving every change firstRecreated promptEvidence: Described by poster
Ary Aranguiz connected ChatGPT to Gmail and asked it to create four labels: ACTION/Reply, ACTION/Decision, ACTION/Review and STATUS/Waiting. ChatGPT then reviewed 204 unread emails from the past seven days and proposed which belonged under each label, separating people waiting for a reply, invitations needing a decision, information to review and routine mail needing no action. It noticed the original label set was incomplete and recommended adding ACTION/Review. Aranguiz approved the proposals, and only then did it create the label and apply the labels. It didn't send, delete, archive, forward or mark anything as read.
ChatGPT · Personal · Source date: