An automation built with Make, OpenAI, Cloudinary and Buffer writes captions, designs content and posts it across social platforms from a sheet.
An automation built with Make, OpenAI, Cloudinary and Buffer writes captions, designs content and posts it across social platforms from a sheet.
The setup starts with one Google Sheets row carrying the post idea, audience and tone. In Make, the flow uses OpenAI to write a caption, generates an image with DALL·E or another image model, uploads that image to Cloudinary, writes the assets back to the sheet, then sends a Slack approval notice before Buffer publishes the post; the person checks the caption and image in Slack and approves it.
The poster says it turns a sheet row into a published social post in under two minutes and can handle the caption, image and posting end to end. They describe it as consistent, but still keep a human approval step before anything goes live.
The main catch is that it is not fully hands-off: approval happens in Slack before publishing, and the builder says they got Make stable by adding error handling and filters.
Build a scenario that reads rows from my Google Sheet [sheet link] containing post topics, writes captions in [brand voice] using OpenAI, creates an image for each, and queues them in Buffer for [platforms]. Mark each row as done once it's queued. Run it on one test row and show me the caption, image and scheduled time before anything is posted publicly.
Reviewers use Make workflows with Gemini to generate ideas, create and title a daily YouTube video, and route Google Form responses into a CRM with follow-ups.
An agent runs overnight, collects the author's AI newsletter subscriptions and produces a daily podcast to listen to on walks.
An hour before each discovery call, get a one-page brief on the account, the attendee and recent news, saved to Salesforce.