Skip to content
TriedPrompts

Land a job after a layoff using a Claude Code job-application workflow you built yourself

Posted
by Mads Lorentzen (GitHub: MadsLorentzen)
Last checked
Method:
How we verify

Evidence: Described by posterThe person describes what happened in words, without screenshots or video.

Outcome

Mads Lorentzen, a geophysicist by training, lost their position in late 2025 and built a Claude Code workflow to run the job search: profiling their own skills, scraping Danish job portals, evaluating fit, and drafting and reviewing each tailored application, plus interview prep. Lorentzen used it weekly and told every employer about it, which they say usually sparked a technical conversation rather than counting against them. Sixty-nine tailored applications, twenty first interviews and one signed contract later, Lorentzen started as an AI engineer in June 2026, and published the workflow as an open-source project.

AI tool

Claude Code

Prompt Recreated prompt

The source didn't share its exact prompt, so we wrote this from what it describes.

What the prompt labels mean

Before you start, ask me 1–3 short questions about anything important that's missing below. Keep them quick. Then do the task, checking in with me at the key points.

Goal: Set up a repeatable weekly job-search routine that finds good-fit roles and drafts tailored applications I review before sending.

What I can give you (ask for whatever's missing):
- My CV and a short summary of what I want next: [CV AND GOALS]
- Job boards or companies to search: [SOURCES]
- Country, language and any must-haves (location, salary, contract): [CONSTRAINTS]

Rules:
- Score each posting against my profile and explain the fit in two or three lines before drafting anything.
- Draft a tailored CV summary and cover letter for good fits, then review the draft against the posting and fix weak spots.
- Use only experience and facts from my CV; never invent skills, titles or results.
- Never submit an application or contact anyone without my approval.
- Keep a simple tracker of what I applied to and when.
- Ask for my OK before you pay, book, send, submit or cancel anything.
- Check facts that can change (prices, opening hours, dates, availability, rules) against the official source, and tell me anything you couldn't verify.

Output: A weekly shortlist with fit notes, reviewed drafts for my approval, and an updated tracker.

You'll know it worked when: I'm sending fewer but better-matched applications each week and getting first interviews.

Try this in:

This prompt has blanks to fill in, like [CV AND GOALS]. We'll copy it instead of filling it in, so you can edit it before you send.

The source used Claude Code, which can take actions on your computer or in a browser. These are general chat tools, so results may differ, and a normal chat may only give you a plan.

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.

Before you start, ask me 1–3 short questions about anything important that's missing below. Keep them quick. Then do the task, checking in with me at the key points.

Goal: Set up a repeatable weekly job-search routine that finds good-fit roles and drafts tailored applications I review before sending.

What I can give you (ask for whatever's missing):
- My CV and a short summary of what I want next: [CV AND GOALS]
- Job boards or companies to search: [SOURCES]
- Country, language and any must-haves (location, salary, contract): [CONSTRAINTS]

Rules:
- Score each posting against my profile and explain the fit in two or three lines before drafting anything.
- Draft a tailored CV summary and cover letter for good fits, then review the draft against the posting and fix weak spots.
- Use only experience and facts from my CV; never invent skills, titles or results.
- Never submit an application or contact anyone without my approval.
- Keep a simple tracker of what I applied to and when.
- Ask for my OK before you pay, book, send, submit or cancel anything.
- Check facts that can change (prices, opening hours, dates, availability, rules) against the official source, and tell me anything you couldn't verify.
- After each interview, help me write down what was asked and prepare for the next round.

Output: A weekly shortlist with fit notes, reviewed drafts for my approval, and an updated tracker.

You'll know it worked when: I'm sending fewer but better-matched applications each week and getting first interviews.

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://github.com/ai-job-search-dev/ai-job-search

  • The day their role was eliminated, a poster started using Gemini as a full-time job-search co-worker. Over three weeks and more than 40 hours, they say it helped them optimise their LinkedIn profile, update their resume, write custom cover letters, networking messages and recruiter follow-ups, and prepare for interviews. They review and challenge everything it produces.

    Gemini · Personal · Source date:

  • A writer fed ChatGPT a job description and their existing application details to produce a tailored resume (two attempts; the first looked too plain), a one-page cover letter and a LinkedIn summary with recruiter keywords. They then asked Gemini to play the hiring manager: it scored them 8.5 out of 10 with 'a very high probability of landing an interview', but said the documents were too 'tech-first' rather than 'finance-first' for this employer.

    ChatGPT, Gemini · Personal · Source date:

  • 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: