Not every automation needs an AI agent. After burning $25+ with a browser agent just to download analytics of my top LinkedIn posts, I decided to build a simple automation tool that costs nothing to run.
--
—
LinkedIn algorithm now prioritizes useful posts and uses saves and followers gained as a signal. So, I wanted to fine-tune my content strategy by analyzing which of my posts gained the most followers and saves - not just impressions or engagement.
LinkedIn has been providing the full analytics which include followers gained, saves and more for a while. But these data are locked behind individual post exports and are not accessible via API.
To get the data manually, it means clicking 60+ posts. 60+ manual downloads. Then somehow combining all the xlsx files.
So I tried an AI browser agent. It worked. But burnt $25+ for scrolling pages, clicking “Export”, and saving files 60 times? That is expensive button-clicking.
The task is completely deterministic. Every page has the same layout, the same button location, the same steps.
So, I thought we don’t need an AI to decide what to do next. We actually just need a script.
So I vibe coded a mini tool with browser automation instead.
What it does:
-
Launches a Playwright browser
-
Opens your LinkedIn analytics dashboard
-
Scrolls through your top posts (by impressions and engagement)
-
Visits each post
-
Clicks “Export” on each post
-
Downloads all the xlsx analytics files
-
Combines everything into one CSV
Simple browser automation. Costs nothing to run.
Video shows it running through my posts. I have sped up and cut the middle part of the video. It took about 9 mins to run.
AI can automate many things. But it is probably overkill or expensive for most automation. Knowing when NOT to use AI is an underrated skill.
I just packaged it as a standalone app, for Mac, Windows and Ubuntu. No coding or setup needed.
Comment “Automation” and connect with me if you want the tool.
#AI #LinkedInAnalytics #Automation #VibeCoding
Enjoyed this? Subscribe for more.
Practical insights on AI, growth, and independent learning. No spam.
More in AI Automation
The most plausible bad outcome of AI (or AGI) is not the rise of Skynet.
It is humans quietly outsourcing our intelligence to AI and we eventually lose it.
AI Coding Assistants Have a Security Blind Spot
A few months ago, I wrote about a non-technical founder whose SaaS got exploited right after he publicly showed his build process using Cursor (https://lnkd....
From ChatGPT to Claude Code: A Non-Techie’s Introduction to the Raw Power of AI by a Techie
Not because I don't like sharing. But because the only tool I use for 99% of my AI needs is Claude Code. And while I think it is not hard to learn, I'm never...
“My challenge in implementing AI is that I cannot justify the use cases to be implemented based on the labor cost in Asia.”
This quote from a COO of an insurance company was on a slide at Apidays Singapore last week. The slide was titled "What are the challenges? - Feedback from t...
If you're still thinking GenAI is just for techies, think again.
A new paper from ChatGPT, based on usage trends from over 18 billion weekly messages, shows how it's becoming indispensable for everyday problem-solving, fro...
Not all AI projects need data scientist and AI engineers.
One of the most common mistakes business leaders make in their AI project is getting the wrong team to build.
The most plausible bad outcome of AI (or AGI) is not the rise of Skynet.
It is humans quietly outsourcing our intelligence to AI and we eventually lose it.
From ChatGPT to Claude Code: A Non-Techie’s Introduction to the Raw Power of AI by a Techie
Not because I don't like sharing. But because the only tool I use for 99% of my AI needs is Claude Code. And while I think it is not hard to learn, I'm never...
If you're still thinking GenAI is just for techies, think again.
A new paper from ChatGPT, based on usage trends from over 18 billion weekly messages, shows how it's becoming indispensable for everyday problem-solving, fro...
AI Coding Assistants Have a Security Blind Spot
A few months ago, I wrote about a non-technical founder whose SaaS got exploited right after he publicly showed his build process using Cursor (https://lnkd....
“My challenge in implementing AI is that I cannot justify the use cases to be implemented based on the labor cost in Asia.”
This quote from a COO of an insurance company was on a slide at Apidays Singapore last week. The slide was titled "What are the challenges? - Feedback from t...
Not all AI projects need data scientist and AI engineers.
One of the most common mistakes business leaders make in their AI project is getting the wrong team to build.