HomeCase studiesMy blog pipeline
Something I built · AI and automation
My blog pipeline
From keyword research to a live, indexed post, with AI drafting and a person approving every word.

The blog on giovanniperri.com, as it looks today.
What I did
A plan built on real searches
The calendar comes from keyword research: Google's suggestions and search volumes from Keyword Planner, collected in my HQ dashboard. After six weeks I re-planned the rest of the calendar from real Search Console data.
A draft on the planned day
On the day a post is due, Claude writes the draft from the plan and from my own case studies, in my tone. It goes to a private copy of the site, and I get an email asking me to review it.
I approve, then it publishes itself
I read each draft in HQ and either approve it or ask for changes. Once I approve, a small job on my computer puts the post live within minutes and asks Google to read it.
Checked after it goes live
Every day the pipeline checks that each live post is in Google's index. If one is still missing after a week, I get an email.
What came of it
Results.
Figures belong to this engagement and this client. Nothing here is an average or a benchmark, and no number appears without the work behind it described above.
What I took from it
AI made the writing fast, but the plan and the approval are what make a blog worth reading. I kept both.
Something similar, at your company?
If I am not the right fit, I will say so on the call and tell you who is.