Activity
Mon
Wed
Fri
Sun
Aug
Sep
Oct
Nov
Dec
Jan
Feb
Mar
Apr
May
Jun
Jul
What is this?
Less
More

Memberships

AI Automation Agency Hub

329.1k members • Free

AI Automation Society

425.3k members • Free

6 contributions to AI Automation Society
How would you scrape a creator's post-engagers into a daily, ICP-scored lead list, without getting your LinkedIn flagged?
Quick context so the question makes sense: I run LinkedIn lead gen (I book qualified sales calls). Right now the way I find prospects is fully manual. I follow a handful of "watering hole" creators in my niche, people whose audience is basically my ideal client. Every time one of them posts something good, I go through everyone who liked or commented, pick out the people who match my ICP, then send a connection request and start a normal human conversation. No pitch, just a real chat. It works. It's just slow because I do all of it by hand. I want to automate the sourcing part. The workflow in my head: 1. Watch a list of creators. When one of them posts, catch it. 2. Pull everyone who engaged with that post (likers + commenters). 3. Enrich and score each person against my ICP (title, industry, company size, signals on their profile). 4. Every morning I get a CSV of the highest-scoring, most relevant people from the last day of engagement. 5. I do the human part myself: connection request + warm DM, zero automation on the actual messaging. The wall I keep hitting is LinkedIn itself. We all know how aggressive it is about automation, rate limits and restrictions. My account is literally my business, so a ban isn't "annoying," it's fatal. So my honest question for the people here who have actually built this kind of thing: If this were your system, how would you build it so it's safe and reliable? Specifically: - Where would you pull the engagers from? Apify actors, PhantomBuster, an unofficial API, a separate throwaway scraping account? What's actually low risk right now? - Would you keep the read-only scraping completely off my main profile, and only ever send connects from the main account? - What daily and weekly numbers do you treat as safe in 2026 for connects and DMs on a warmed account? - For scoring/enrichment, what are you using? Clay, a custom LLM step, something lighter? - And honestly, where's the line where this stops being worth automating and
Bye Bye to Manual lead finding and researching it.
Now Imagine An automated pipeline that turns a short prospect description into a verified, ready-to-contact lead list - no manual research required. I Built this "LinkedIn Lead Scraper & Enrichment Workflow" With the help of Claude code. What it does? ~You describe the kind of person you want to reach — job title, industry, location, and company size. ~The system searches LinkedIn for matching people. ~verifies and enriches each one with a work email, phone, and company website. ~fills in any gaps with a web search. ~Delivers the finished list straight into a shared Google Sheet. ~Every contact is deduplicated automatically, so re-running a search never creates repeat rows ,it just keeps existing contacts up to date. The Pipeline:- (Five automated stages run in sequence for every search) 1).Define the target:-You submit job title, industry, location, and company size through a simple form. 2).Search LinkedIn:-Matching profiles are pulled directly from LinkedIn based on your criteria. 3).Verify & enrich:-Each person is matched against a business database for a work email, phone, and company site. 4).Fill the gaps:-If anything's still missing, a web search finds the company's official site. 5).Deliver & dedupe:-The finished row lands in your Google Sheet — updating any existing match instead of duplicating it. Dropping a proper demo video of this workflow tomorrow.. I would like to hear from you guys, feedbacks are always welcomed 👇 Harsh Singh
Bye Bye to Manual lead finding and researching it.
0 likes • 1h
@Harsh Singh I understood the workflow, nice man 💪🏻. I have two questions. Why did you choosed Apify and the other thing is with this workflow can you give a creator and then the workflow to see the latest post of this creator and to see the people who have liked the post and to scrape them whether they are your ICP. That will be supe ruseful for me if you know how it can be done without having problems with LinkedIn and havinfg the cance of being restricted
Welcome! Introduce yourself + share a career goal you have 🎉
Let's get to know each other! Comment below sharing where you are in the world, a career goal you have, and something you like to do for fun. 😊
5 likes • 5d
Killed my agency last year after a 596K-impression campaign taught me a brutal lesson Hey everyone 👋 Kaloyan here, 19, from Sofia, Bulgaria. Bit of a confession since this room is all about getting paid for what we build. Last year I co-founded a LinkedIn agency. One campaign we ran hit 596,806 impressions in 16 days — 15 people, zero ad spend. Looked amazing. And the business still almost died — because impressions don't pay rent. Booked calls do. That lesson cost me three months and a co-founder. So I scrapped it and got obsessed with one question: what actually turns LinkedIn attention into booked sales calls? I'm building the answer into kalitora.com now but the real work is the daily experiments on my own profile: lead-magnet formats, hooks, comment-to-DM flows. I keep every number. Why I'm actually here: most of you are miles ahead of me on n8n and agents I want to learn that properly, because half my experiments now need automation I can't build yet. So here's a fair trade: if you ever have a LinkedIn question lgorithm, content that converts, profile setup, turning post-commenters into actual conversations ask me. Straight answer, real numbers. And a genuine question for the agency owners here: where do your clients actually come from today? Referrals? Cold outbound? Content? I'm trying to map what's really working for people who've already got something running - curious what you'd say.
1 like • 5d
@Julius Waggoner Thanks for the warm welcome
Cold calling buddy
Hey everyone, I run an AI automation agency from home based in the UK London. Recently, my pipeline has been a bit slow, so I set a strict goal for myself: cold calling 5 hours a day on Monday to Friday. But honestly? I've still been procrastinating. 😅 I actually worked as an appointment setter a few years ago, so the skill is in me. The problem is that working from home means I'm missing that bustling "sales floor" energy, which makes it so much harder to just pick up the phone and get started. I already use Focusmate to body double for my development sessions, and it works wonders for keeping me on track. I want to apply that same concept to sales. Here's what I'm looking for: - Another appointment setter or founder who also needs to make cold calls. - We hop on a Zoom/Google Meet, quickly state our goals for the session, mute our mics, and dial for 50 minutes. - Afterward, we unmute, recap how we did, and hold each other accountable. I think doing this with someone else who is also making calls would create a great "power hour" energy to get our motivation up and generate more sales. Is anyone in a similar boat and want to partner up for some sessions? Shoot me a DM or comment!
0 likes • 5d
The procrastination confession made me laugh because it's all of us. Focusmate for sales calls is genuinely smart. If you want a co-founder-type body double for a session, I'm up for it need to grind outreach too and the mutual accountability sounds perfect.
AI 2040: the sequel to AI 2027 nobody's talking about yet
read something today thats been stuck in my head. the team behind AI 2027 https://ai-2027.com/ put out a follow up, AI 2040. if 2027 was the warning, this is the "ok so what do we actually do" part. the idea is kind of wild. they basically say if the race to superintelligence keeps going like now, it ends bad. either we lose control or power ends up in the hands of like 5 people. so instead of just predicting that, they wrote out the good ending and called it Plan A. Plan A is: slow down on purpose. push superintelligence back to 2040, make all AI research public so no country can hide what its building, set it up so nobody can secretly sprint ahead. kind of like the nuclear standoff logic but for compute. and they dont even say this is what WILL happen. its what they think should happen. then they map out 4 darker paths for if we dont. honestly i hope it goes something like this. would be kind of incredible if it actually did. but a whole "everyone slows down together" global deal is a big ask, im not naive about it. so whats your read, is slowing down on purpose even possible or are we already past that point? and if you got your own version of how the next 10 years go, drop it, id genuinely like to hear it. https://ai-2040.com/
1 like • 5d
The "slow down on purpose" idea is interesting but Ian's right that it's unlikely without enforcement. No individual actor slows while competitors sprint. What I find more useful as an operatorinstead of betting on the macro outcome, focus on staying adaptable enough that either ending doesn't wreck you. You can't control the race you can control whether you're building on rented land.
1-6 of 6
@kaloyan-anastasov-1855
Building kalitora.com: booking founders 20-30 qualified calls/mo from LinkedIn. Sharing every experiment's numbers. Bad at n8n - here to learn 🇧🇬

Online now
Joined Jul 10, 2026
Powered by