◆ LinkedIn

Write an article

This is real work, not a feature someone invented — it comes from real job ads and real questions people asked. Below are four ready AI prompts: get it done, make it easy for the next person to say yes to, work out the right move when you are stuck, and stop it coming back.

4prompts
See the prompt↓All LinkedIn tasks

The same task, four prompts

today's deadline · the next reviewer · the stuck moment · the pattern
AExecute — do the immediate taskI need to publish an article that proves I understand hiring challenges for early-stage…+
I need to publish an article that proves I understand hiring challenges for early-stage startups. Draft a 650–850 word piece titled ‘How We Lost Four Great Candidates — and What We Fixed’ that opens with a specific hiring miss at my company last quarter, names the role (Senior Backend Engineer), the candidate’s key objection (unclear career path), and the recruiter involved (Maya Ortiz). End with three concrete changes we implemented and one measurable outcome to share with hiring managers this week.
when the reply comes backPush once: ask it to sharpen the weakest part, and to say what it assumed. Helpful?
BImprove — make it easier to acceptBefore I post this article to my profile and tag founders in my network, make it easy to skim…+
Before I post this article to my profile and tag founders in my network, make it easy to skim for busy hiring leads: pull the savings and impact forward into a 3–line summary under the headline, bold the three new hiring changes, and flag any sentence that could read like bragging or legal overclaim so I can tone it down.
when the reply comes backPush once: ask it to sharpen the weakest part, and to say what it assumed. Helpful?
CDecide — diagnose the stuck momentWe were three rounds deep with Priya, offered market pay, and she dropped out citing no clear…+
I just lost a candidate at final offer who said there was no growth path
We were three rounds deep with Priya, offered market pay, and she dropped out citing no clear path to lead. I can’t tell whether the real reason was money, product maturity, or my team’s vague org chart. What likely happened and what should I say to Priya now to salvage the relationship?
when the reply comes backPush once: ask it to sharpen the weakest part, and to say what it assumed. Helpful?
DBecome — change the patternAcross five hires last year we lost people after final interviews for the same reason: they…+
We repeatedly lose candidates late due to vague career progression
Across five hires last year we lost people after final interviews for the same reason: they couldn’t see a path to progress. Where should I change my hiring habit — job descriptions, interview questions, offer conversations, or internal org updates — so candidates stop folding at the finish line? Recommend one new habit to adopt this quarter and a simple metric to track.
when the reply comes backPush once: ask it to sharpen the weakest part, and to say what it assumed. Helpful?

Questions people actually ask

honest answers, no sign-up

Every task here was seen in the real world. Someone doing the job named it, a real job ad asked for it, or a lot of people asked about it online.

If nothing real showed a task, it is not on the page. That is the whole rule.

They are the same job approached four ways, because what you need depends on where you are.

Get it done today. Make it easy for the next person to say yes to. Work out the right move when you are stuck. Learn the pattern so the job stops coming back.

For most of these jobs it can carry the heavy thinking - draft it, sort it, check it, rehearse it with you.

It cannot sit in your chair, take the blame when a number is wrong, or notice what nobody wrote down. Let it do the first 80%. Keep the last 20% that is truly yours.

No. Copy any prompt and paste it into the AI you already use. No account, no score, no wall in the way.

Any of them. The prompts describe the work rather than naming a product, so they are not tied to one assistant.

That is also why they keep working when you switch.

Change it freely. Every prompt is a starting line, not a rule.

Put in your real numbers, your real names and your real deadline. The more you make it yours, the better the answer comes back.

The tasks come from real job ads, published job data and the questions people ask in public forums.

The steps come from LinkedIn's own documentation, with practitioner sources for the traps the manual does not mention.

Push once. Ask it to sharpen the weakest part and to say what it assumed.

Most wrong answers come from a missing detail rather than a bad prompt - tell it the thing it could not know.