Social Media Post Generation Automation - Twitter

We designed an user-friendly interface that allowed our client to feed in URLs of news articles. The application, built with FastAPI and ChatGPT-3.5-Turbo model, processed these articles and generated tweet options. This solution increased our client's posting frequency, driving a significant growth in follower count.

Content Marketing
Product Development
AI Marketing


Our client wants to expand their reach on Twitter by attracting more followers. However, due to time constraints, they required a solution that would automate the process of generating tweets using industry news. 

The client's involvement should be limited to selecting news articles and choosing their preferred tweets from a list of generated options.

What’s a Rich Text element?

The rich text element allows you to create and format headings, paragraphs, blockquotes, images, and video all in one place instead of having to add and format them individually. Just double-click and easily create content.

Static and dynamic content editing

A rich text element can be used with static or dynamic content. For static content, just drop it into any page and begin editing. For dynamic content, add a rich text field to any collection and then connect a rich text element to that field in the settings panel. Voila!

How to customize formatting for each rich text

Headings, paragraphs, blockquotes, figures, images, and figure captions can all be styled after a class is added to the rich text element using the "When inside of" nested selector system.


To address this challenge, we developed a straightforward user interface that enables the client to add URLs to news articles or news pages. 

Our application then scrapes the content from these sources and converts them into Markdown format. 

Leveraging a combination of prompts, we extracted key benefits from the articles and presented them as engaging tweets.


We implemented different options on how to generate the tweets, our most compelling approach integrated facts from different news articles to generate unique content that surpassed a simple summary.

The facts are stored in a vector store and pulled based on the topic of the provided news article.


Fig. 1: Screenshot of the Proof-of-Concept.


  • The client uses an average of 2 out of 10 generated tweets.
  • Previously, the client used to post once a week, but now it’s 1 – 2 times per day.
  • Within the first month, there was an approximately 12% increase in followers.



  • Use interface: Next.js
  • Core application:
  • FastAPI python application
  • ChatGPT-3.5-Turbo model
  • Deployment as docker application

Ready to get started? Schedule a free consultation

Erik ConsultantConsultant

Schedule a meeting

Let's discuss your idea, and ROI estimation.

How AI/ML can be applied to your business.

Or whatever else you want to discuss about!
(We can sign an NDA!)

Prefer to write us?
Prefer to write us?