When Google unveiled Gems I was really excited. For me Open AI’s Custom GPTs was essential functionality Google Gemini was lacking. The addition of a Customisable AI Chatbot to Gemini would go a long way to bridging the gap in terms of user experience. Unfortunately, after testing the reality is that Gems are missing some really important features and as a result I expect most users will stay with ChatGPT. More than anything Custom GPT’s are just more accessible and also just seem to make more sense.
Gems vs Custom GPT’s
Feature | Gems | Custom GPT |
Ability to give instructions | Yes | Yes |
Ability to save and come back to the Custom Gem/GPT | Good | Good |
Add knowledge base files | No | Yes |
Able to share GPT/Gem with Colleagues | No | Yes |
Able to share GPT/Gem with via URL only | No | Yes |
Able to share GPT/Gem Publicly | No | Yes |
Gem/GPT Store | Google only Gems | GPT's from Open AI & any creator |
Lack of Knowledge Base Integration: Of all the features this is the one I just do not understand Google leaving out. For me the blend of an AI tool with your own knowledge files is the main benefit of a custom GPT. This allows you to easily instruct the custom tools to reference these files plus you can update and replace the files easily. You can do something similar with Gems but the files will need to be added via the conversation which is messy and confusing.
No Sharing Capabilities: Unlike Custom GPTs, (which can be private, shared with your team, shared via a private URL or published publicly) Gems are private. This severely limits their utility, especially for teams or businesses looking to implement AI solutions across their operations.
No Public Accessibility: Another major drawback is the absence of a public platform for Gems. At present you can only access other Gems that have been created by Google. Custom GPTs can be published on the GPT store, allowing anyone to access and benefit from them. However, I should add that the ability for anyone to publish a Custom GPT on the GPT store is a double edge sword. It is a huge benefit for publishers but means that quality of Custom GPT’s can vary wildly by published and you never really know what you are getting. So in this regard I can understand why Google has refrained from launching a full GPT store equivalent.
Why Custom GPTs Still Lead the Market
In contrast to Gems, Custom GPTs remain the go-to for those looking for accessible, customisable, and shareable AI tools. Whether you’re looking to automate customer service, streamline content creation, or develop industry-specific AI solutions, Custom GPTs offer a robust platform with the flexibility and power needed to get the job done.
Google’s attempt with Gems, while an interesting concept, misses the mark by not offering the depth, customisation, and usability that have made Custom GPTs a favourite among users.
Ultimately Google’s Gems have fallen short of expectations. Without the ability to share, integrate with knowledge bases, or be published for public use, Gems are more of a minor convenience than a ground breaking innovation.
If you’re serious about leveraging AI in your business or personal projects, Custom GPTs are still your best bet. Google’s Gems might make returning to a conversation a bit easier, but anything you can do with a Gem can just as easily be achieved within an existing, well-labelled conversation with Gemini.
For now, ChatGPT’s Custom GPTs remain the most accessible, powerful, and user-friendly AI tools on the market. Google has missed the mark this time, but I’m sure things will continue to change at a rapid pace and this blog post could be irrelevant in just a few weeks time!
More reason to stay tuned as the AI landscape continues to evolve. Hopefully, Google’s next attempt will hit closer to the mark.
Comments