Performance Marketing & AI Automation
I work where performance marketing, e-commerce and AI automation meet. I read the data, set up tests, turn manual work into systems and keep my eye on results.
Tools I use
Websites, paid ads and AI automation. Each project page has the screenshots and a step-by-step account of what I did.
I built myself a practice app for the 82-video Spanish series I follow on YouTube. Claude Code reads the videos’ subtitles and writes a short explanation and exercises for each lesson. I can’t move on until I score 80% on the current one.
Read the caseDrag to explore · click a node
Yesterday’s Meta ad results land in Telegram at 08:00 every morning. Any ad set that got more expensive, spent without bringing in a message, or saw its frequency climb while costs rose is flagged on the first line.
Read the case
I built myself a Spanish app to turn idle minutes on my phone into vocabulary practice. I wrote the rules and screens in a Word document and shipped it with Claude Code in two days. It has 1,500 words, and a word only counts as learned after 2 correct answers on 5 different days.
Read the case
I built a dashboard that reads sales, customer and expense records from Google Sheets and shows revenue, gross profit, open jobs and targets on one screen. The demo here runs entirely on sample data.
Read the case
One QR code on the counter turns the moment of payment into a follower and a Google review. Customers who visit the shop no longer vanish once they walk out the door.
Read the case
I designed and built the site you’re reading with Astro. Every number has a screenshot next to it, the n8n workflow can be explored in the browser, and adding a new project is a single markdown file.
Read the case
I rebuilt the Wix site from scratch with Astro. Seven services written in the language of search, an 83-question FAQ marked up with schema, and every phone tap tracked.
Read the caseDrag to explore · click a node
Mockups went from 3 min to 45 s, listing prep from 15–20 min to 2 min.
Read the case
1,158 customer conversations from ads at TRY 10.47 each. Google Business Profile interactions above the previous year for five months running.
Read the caseMost of marketing is operations. These workflows cut long tasks short.
Before
Filling in a listing’s title, tags, description, attributes, price and SKU one field at a time took 15–20 minutes.
After
A GPT I built pulls the SEO data, it lands in Sheets and gets matched by SKU, and an n8n workflow prepares the listing on Etsy as a draft. I deliberately kept publishing manual.
Input
What the rulebook checks 7 sections
A selection from the rule set I wrote; I don’t share the full text.
Sheets row — 42 columns
Columns 1–33 belong to the GPT. Columns 34–42 (price, quantity, folder, listing ID, error, timestamp) are n8n’s — once it opens the draft, it writes the listing ID back to the same row.
Before
Placing an image into the mockups and exporting it in Etsy’s format took 3 minutes. A 30-image batch meant an hour and a half — and on repetitive work, the more tired you get, the more likely a skipped mockup or a file in the wrong folder.
After
The script I wrote does all the placing and exporting in one go. On 30-image batches it brings the error rate to zero: no skipped mockups, wrong sizes or files in the wrong folder.
3× speed
Before
I came up with image ideas one at a time; each time I had to rethink what the store was missing and what people were searching for that season.
After
I defined the rule set myself, based on the store’s niche. The GPT looks at what’s being searched that season and produces ideas in batches of 25 prompts.
Input
Column names don’t have to match exactly; fields are matched by meaning.
What the rulebook checks 7 sections
A selection from the rule set I wrote; I don’t share the full text.
Output for each idea
Prompts are in English, the batch summary in Turkish. Each idea carries a selection reason — so the gap it fills can be discussed later.
The ones I actually use day to day. Where and how I used them is covered on the project pages above.
I try to understand the market, competitors and demand through data. I make a point of not starting from a guess.
I do the work by hand for a while. That’s how I see which steps repeat, where the time goes and what can be automated.
I quickly turn the repeating step into an automation and set up measurement at the same time; I don’t move on without seeing the result.
If the result is good, I fill the gaps and extend the setup. If it isn’t, I don’t pour more time into it.
What keeps me in marketing is data: making a decision with numbers I’ve measured, not with a guess.
I started out with Amazon dropshipping. I was twenty; I learned product research, listing and selling, but I didn’t understand the accounting side. When I couldn’t manage cash flow, I had to shut it down. The lesson I took from it: a sales figure on its own says nothing — you have to be able to read the numbers behind it.
I chose digital marketing because I enjoy digging into data. Seeing what an audience searches for, what it clicks and where it drops off takes the guesswork out of the job. Automation gives me freedom with my time: most of marketing is repetitive operations, and once a machine takes that over, what’s left is the work that takes thinking, testing and reading results.
I’m currently looking for a full-time role. I want to join a team that measures results, where I can use performance marketing and automation together.
If you’re hiring
The work here is a more detailed version of the lines on my CV. If one catches your eye, its page has the screenshots.
For freelance work
For freelance work, a collaboration or just a question, write to me directly. I usually reply the same day.
Address: omerfaruktataroglu@gmail.com