OpenAIClaudeGoogle AI SearchPerplexity
Ask AI →
TL;DR
A job search is a matching problem with a volume problem attached. Claude does both: it reads your CV, tells you which roles you actually qualify for and which keywords the ATS screens for, builds a match-scored shortlist from LinkedIn and Indeed, then applies with a tailored CV per role.
Watch · under a minute
The four prompts
Run them in order.
1
Act as a senior recruiter. List the 20 job titles I am most qualified for and the exact keywords each ATS scans for.
Upload your CV first. The keywords come from what you already have.
2
Rewrite my CV into a master template I can tailor instantly.
One source document. Every tailored version derives from it.
3
Go to LinkedIn and Indeed. Find every job matching these titles. Build a spreadsheet with a match score and a tailored CV for each.
Turn on agent mode. This is the step that browses.
4
Apply to the top 100 matched jobs, customising each application to the job description.
The part that runs while you do something else.
Credit: @milesreevesai on TikTok

Most job searches fail on arithmetic. You are one person applying to roles one at a time, while the system on the other end is filtering on keywords your CV may not contain. The volume problem and the matching problem compound, which is why a strong candidate can send forty applications and hear nothing.

This workflow treats both as one job. It is four prompts, and only the third one needs agent mode.

Step one: let Claude tell you what you qualify for

Upload your CV and ask it to act as a senior recruiter. The useful version of the prompt asks for two things at once: the twenty job titles you are genuinely qualified for, and the exact keywords each ATS scans for. That second half is what most people skip, and it is the half that decides whether a human ever sees the application.

Step two: one master CV, not forty versions

Ask Claude to rewrite your CV into a master template you can tailor instantly. One structured source document, with the step-one keywords in the right places. Every tailored version after this is an edit, not a rewrite.

Step three: let it browse

Turn on agent mode and give it the search. Go to LinkedIn and Indeed, find every job matching those titles, and build a spreadsheet with a match score and a tailored CV for each. The spreadsheet is the deliverable that matters, because it turns an unbounded search into a ranked list you can inspect before anything goes out.

You are not sending a hundred identical applications. You are sending a hundred applications that were matched to a posting before they were written.
Source: Chief Content Marketer

Step four: apply, with a tailored CV each time

Then the instruction that saves the hours: apply to the top hundred matched jobs, customising each application to the job description. Claude works the list while you do something else.

1
spreadsheet you actually read before sending anything. The match score is the difference between a targeted search and a spray-and-pray tool.
When to use it
This is for a real search with real volume: a career change, a layoff, a relocation. For two or three roles you already know, write the applications yourself. The machine earns its keep at forty roles and above.

Where it breaks

Three honest limits. Agent mode browsing LinkedIn is the fragile part; the site does not love automation, so supervise the search step the first time. A match score is a model judgement, not a decision, so read the top of the list before you commit. And tailoring clears the filter, it does not make you qualified, so do not let the volume outrun your judgement about fit.

Used as a filter, this is a force multiplier. Used as a volume machine with no human read of the shortlist, it just gets you to a hundred rejections faster.

Get Smarter With AI, Every Week
Practical AI workflows for content marketers, one short email at a time. No fluff, no vendor spam.
Subscribe Free →
Privacy Policy