Want to create an AI agent—something that can reason, act, and automate tasks—without writing a single line of code? This video tutorial walks you through exactly that. In just ~20 minutes, you’ll learn how to set up a working AI agent, connect tools, give it memory, and have it perform actions automatically.
Here is a breakdown of the tools and process described in the video:
- Make.com: This is the core platform where you will build the automation by connecting various modules.
- Gmail: The process begins with a Gmail module that acts as a trigger. It is configured to watch for new emails with a specific subject, such as “headline AI.”
- Text Parser: This module extracts the news article URL from the body of the incoming email.
- HTTP Request: This module is used multiple times throughout the workflow:
- To get the content of the news article from the extracted URL.
- To send a request to Nano Banana (also known as Gemini 2.5 flash image preview) to generate a meme image.
- To send the generated image to Cloudinary to get a shareable URL.
- Google Gemini: This module analyzes the article content to create a “meme plan.” It returns a structured JSON output with details like the meme template, top and bottom text, and the final tweet text.
- JSON Parser: This tool is used to extract the specific variables (e.g., top text, bottom text, tweet text) from the JSON output provided by the Gemini module.
- Cloudinary: This service hosts the generated image and converts the base64 string into a public URL.
Leave a Reply