◆ LinkedIn

Moderate group discussions

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 you to keep the product-management group civil this week. Scan new posts and the top 20…+
I need you to keep the product-management group civil this week. Scan new posts and the top 20 comments every morning, remove spam or self-promotion that isn’t tied to product practice, and flag any thread where tempers flare or someone posts confidential company info. When you flag, add one-sentence context: who posted it, which company they name, and why it troubles community norms. Follow up after removal with a private note to the poster explaining the rule and next steps.
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 a sticky about interview techniques, make it clear why members should read it:…+
Before I post a sticky about interview techniques, make it clear why members should read it: surface the biggest benefit in the first two lines, summarize three quick takeaways, and call out any sections that might trigger heated debate (salary, hiring bias). Also point out where comments will add value versus where they’ll derail the thread.
when the reply comes backPush once: ask it to sharpen the weakest part, and to say what it assumed. Helpful?
CDecide — diagnose the stuck momentTwo senior PMs have started a heated exchange about take-home tests; one accuses the other of…+
Two members are arguing about whether take-home tests are fair
Two senior PMs have started a heated exchange about take-home tests; one accuses the other of elitism and the thread is attracting outsiders. I’m worried this will split the group and chase away junior members. I don’t know the posters’ full histories or whether either is a serial provoker. What’s the least escalatory step to calm the thread, what wording do I use publicly, and how should I privately message the two participants to reduce repeat incidents?
when the reply comes backPush once: ask it to sharpen the weakest part, and to say what it assumed. Helpful?
DBecome — change the patternOver the last six months the product group keeps getting flooded with vendor pitches and…+
Persistent unhelpful commenting and shifting threads off-topic
Over the last six months the product group keeps getting flooded with vendor pitches and off-topic rants after high-engagement posts. Each cleanup takes hours and members complain about noise. What habitual moderation changes should I make so fewer posts go off the rails, how do I communicate new norms to the 8,000 members without alienating contributors, and what one enforcement action will stop repeat offenders?
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.