Why Custom GPTs are better than plugins, for creators and users!

On November 6, 2023, OpenAI announced Custom GPTs. Since then, over 3 million GPTs have been created, with over 200.000 of them made publicly available.

Fundamentally, Custom GPTs come with pre-configured actions and capabilities (e.g., do something in app “X”), as well as specific embedded knowledge for the task they have been built for. That also means that instead of users having to turn plugins on & off manually, they can switch conversations depending on the task, which usually is way quicker and more intuitive.

Here are the five biggest reasons GPTs are significantly better than plugins for developers and users.

If you haven’t tried a Custom GPT yet, try the Forms, Checklist & Workflows GPT for starters. (Full disclosure: I built that one 😉)

1. Open to everyone

The biggest thing that a lot of developers waiting to get invited by OpenAI to write traditional plugins are missing is that you can not only do the same but more with GPTs, but also that in contrast to publishing plugins, GPTs can be listed on the “GPT Store” or simply by sharing a direct URL. Which ultimately results in way more GPTs being made available than plugins.

That’s also why there are 2000 times more GPTs than plugins publicly available already today!

2. Knowledge

Instead of cluttering your system message (or, “instructions”), adding knowledge to your GPT is as easy as uploading a file.

These files can be everything from PDFs, Raw Text, or Markdown (e.g., exported Notion Pages).

3. Capabilities (Web Browsing, DALL·E Image Generation & Code Interpreter)

Depending on the context of GPT, you can enable/disable specific inbuilt capabilities from ChatGPT for the conversations.

Writing a “book creator” GPT? Just enable DALL-E Image Generation to allow users to generate fitting pictures along with the story!

4. Conversation starters

Previously, people had to try plugins to somehow get an idea of how to use them and what good examples to use them for. But with easy-to-add conversation starters, GPT creators can give users a couple of suggestions based on what their GPT is good at.

5. No code, no servers.

For best results, you’d still want to integrate with your product API. Especially if you aim to get more users to discover your product and services via the GPT. But the great thing is for pure “knowledge” driven GPTs, creators don’t even have to do that. Instead, all they need to do is add an “instruction” paragraph (to provide the GPT with necessary context) and upload your knowledge as files.

Tada! No code, no databases, no servers…

6. GPT @Mentions

As of this morning, OpenAI supports mentioning GPTs from within conversations of another GPT. This allows you to ask a GPT for the Top 10 games for Switch, and then mention the Forms, Checklists & Workflows GPT to create a checklist for you to tick off a game you played or beat.

All the other reasons, and why you should subscribe 😋

Looking past all these advantages of GPTs over Plugins, it’s often easy to forget the main benefits of creating either. Being:

• Creating something truly impactful with a small amount of work.

• Bringing your existing product API and specification, rather than writing new code

• Defining actions with different authentication models depending on your needs (None, API Key, OAuth 2.0).

• Leveraging ChatGPT as the best user acquisition channel you’ve ever had.

Are you curious about the last point in that list? Hit the button below! 😇