Keeping a Google Business Profile active with real job photos and AI-written posts
Four Make scenarios keep local businesses' Google Business Profiles active. Three, one per client, pick an unused job photo from the client's Drive folder every couple of days, have ChatGPT write a local post around it and publish it; a fourth adds a fresh photo to a profile's media each day. A Google Sheets log of used photos means no photo goes up twice.
Where this applies
Local-SEO and marketing agencies, and any home-service business that wants its Google Business Profile kept active with real job photos.
- modules from photo to post
- 8
- between posts per profile
- 2 days
- scenarios, one per profile and task
- 4
The problem
For a tree surgeon or a builder, the Google Business Profile is the shop window, and fresh posts and photos are part of what makes a listing look active and real. The material exists in the photos crews take on every job, but posting it is nobody's job, so profiles go quiet for months.
Scheduling tools still need someone to load the queue. What a busy agency needs is a loop that draws on the photos the client already drops in a folder, writes something sensible about each one, and never posts the same photo twice.
What we built
A log decides what is new
Each run starts by reading the client's log of photos already used and joining their names into one string with a text aggregator. It then lists the files in the client's Drive folder and filters out every file whose name is in that string. What survives is the pool of unused photos.
One photo, one post
An array aggregator gathers the pool and a variable picks one photo from it. ChatGPT writes a post around it for that business and its area, and the scenario publishes it to the profile through the Google Business Profile module.
Log last, so nothing repeats
The final module adds the photo to the log. The next run's filter excludes it, so the rotation works through the folder without repeats, and the sheet doubles as the client's posting history.
One template, cloned per client
Each client has a copy of the same eight-module scenario in its own folder, pointed at its own Drive folder, log and profile. The photo-upload variant drops the AI step and adds a photo to the profile's media every day instead of writing a post.
The outcome
The posting copy read in detail ran every two days or so throughout the 30 days to 21 October 2026, at eight credits a run, most recently on 19 October.
The daily photo upload ran every day in the same 30 days, most recently on 20 October.
Where it stops
The AI-written post is published without a person reading it first. The rotation depends on someone adding photos to the folder; once every photo has been used there is nothing new to post. Each client runs its own copy, so a change to the template has to be made in each one.
Built with
- Make.com
- Google Business Profile
- Google Drive
- Google Sheets
- OpenAI
Patterns used
- Used-item log as a filter
- Aggregate, then pick
- Log last
- Template cloned per client
Page copy drafted with AI assistance. Skofi is accountable for it. Editorial policy
Have something shaped like this?
If any part of the above resembles a problem you are living with, a short call is the fastest way to find out whether it is the same problem underneath.
What happens on the call
- 15 minutes, no deck
- We map the process on the call
- A written scope, or an honest no