Connecting Make Automation with Custom GPTs

I’m interested in connecting Custom GPTs that we can make on Open AI with Make. Is this currently possible?

Heres an example of someone doing it with Zapier, but it would be much more powerful with Make

1 Like

This is a new feature and there are no modules for the OpenAI app in Make yet.

If the external service has a Developer API Reference/Documentation then you should be able to integrate the endpoints in Make using the generic HTTP “Make a request” module.

You linked to the feature overview where it states:

At a high level, a typical integration of the Assistants API has the following flow:

  1. Create an Assistant in the API by defining it custom instructions and picking a model. If helpful, enable tools like Code Interpreter, Retrieval, and Function calling.
  2. Create a Thread when a user starts a conversation.
  3. Add Messages to the Thread as the user ask questions.
  4. Run the Assistant on the Thread to trigger responses. This automatically calls the relevant tools.

By clicking the documentation links above, you can view the endpoints you can use for the “Make an API Call” modules. This means you’ll need at least four operations just to setup and initially run a new assistant.

You can also submit module suggestions to the Idea exchange, under App improvement ideas. Don’t forget to search for it first, just in case someone already suggested it!

4 Likes

Here’s a quick simple tutorial on how to connect to your make automations through GPT actions in your GPTs:

5 Likes

Can you help me how it use with API assistant? I already have connected API asistant with Messenger (i used Python code in Replit + ManyChat), but i need setup in agent connection to make.com

Can you help me with this?