How to build your own customized Google Gemini AI chatbot

(Image credit: Google)

Google is rolling out the ability to build custom versions of its Gemini AI chatbot tailored to specific tasks and preferences first seen at this year’s Google I/O event. These ‘Gems’ are essentially Google’s equivalent of the Custom GPTs found in the GPT Store run OpenAI on ChatGPT.

Gems are pitched as personalized AI experts that are ready to go immediately after they are built and don’t require you to continually redo prompts to adjust the general Gemini model for your purposes. Instead, subscribers to Gemini Advanced or those using the business and enterprise versions of Gemini can quickly dive into whatever role they want Gemini to take on for them. Gems are available on both desktop and mobile devices in more than 150 countries and in many languages.

You can build a Gem in much the same way you’d build a CustomGPT. Simply describe the kind of expert you want or the tasks you have in mind, and Gemini will convert what you write into specialized instructions for Gemini. Simply name it, and you will be good to go. You can see how it works in the video below.

Polished AI Assistance

As a demonstration and to prime the pump for new Gems, Google has already set up several pre-made Gems for users. They're somewhat broad but cater to common requests made of Gemini. The pre-made Gems include a tutor that simplifies complex ideas called Learning Coach, an idea generator called Brainstormer, a tool for helping find and get a job called Career Guide, a software programming assistant called Coding Partner, and the aptly named Writing Editor for exactly what the name says.

Like the newly upgraded Imagen 3 AI image maker, Google clearly sees Gems as a good way to entice and keep users on Gemini. Embedding it into the platform could give Google an edge in attracting users who are looking for advanced yet accessible AI tools. It's part of the larger plan to make Gemini central to your life as much as possible. And, if you don't like the way Gemini works out of the box, you can now polish it to look and perform the way you prefer.

Eric Hal Schwartz is a freelance writer for TechRadar with more than 15 years of experience covering the intersection of the world and technology. For the last five years, he served as head writer for Voicebot.ai and was on the leading edge of reporting on generative AI and large language models. He's since become an expert on the products of generative AI models, such as OpenAI’s ChatGPT, Anthropic’s Claude, Google Gemini, and every other synthetic media tool. His experience runs the gamut of media, including print, digital, broadcast, and live events. Now, he's continuing to tell the stories people want and need to hear about the rapidly evolving AI space and its impact on their lives. Eric is based in New York City.