Today, Google and Udacity announced a free online course that teaches developers and designers how to use Google AI Studio and the Gemini API to build generative AI capabilities into their applications, websites, products, services, and operations.
This course, developed in collaboration with Google and Machine Learning @ Berkeley, will be available through Udacity starting today. By the end of the course learners will be able to:
- Describe the fundamental concepts behind LLMs and Gemini models
- Differentiate between common prompting techniques, such as zero-shot, few-shot, and chain-of-thought prompting
- Efficiently use Google AI Studio for designing prompts
- Utilize the Gemini API effectively, including core components such as making calls, configuring parameters, sending prompts, and receiving results
- Construct an application leveraging the Gemini API
Udacity was founded with the advent of AI education online. Udacity began when Stanford instructors Sebastian Thrun and Peter Norvig had a revolutionary idea to offer their “Introduction to Artificial Intelligence” course online—to anyone, for free. This release is part of Google and Udacity’s broader mission to democratize AI development and make AI learning more accessible.
Generative AI has rapidly become the most sought-after capability across sectors. With the Gemini API, developers can easily integrate the largest and most capable AI model from Google into their apps, regardless of platform, interface, or industry. This makes acquiring practical knowledge related to integrating AI into new and existing web and mobile applications with Gemini a highly marketable skill.
The course is taught by Rohan Viswanathan, Vanessa Teo, and Derek Xu of Machine Learning @ Berkeley, and the curriculum includes Large Language Model (LLM) prompting techniques and design best practices with Google AI Studio and how to develop with Google’s LLM, Gemini via the Gemini API.
Google AI Studio is an easy-to-use, browser-based tool that lets users quickly prototype prompts for Gemini. The Google Gemini API makes it easy for users to start developing generative AI applications that work with text, images, and code, with just a few lines of code. The Google Gemini API and Google AI Studio are available in these countries and territories.
![](https://www.udacity.com/blog/wp-content/uploads/2024/07/inline-image.png)
Udacity has been globally recognized for its effectiveness in helping learners develop real skills that are transferable to jobs in tech. When users complete the Gemini API by Google course they will have developed skills in LLMs, prompt engineering, Google AI Studio, and the Gemini API. Learners can use their LLM skills to leverage LLMs for a variety of tasks, including text generation, translation, summarization, and question-answering, understanding their architecture, and the ethical considerations in their use. The Google AI Studio skill allows learners to customize the behavior of a generative AI model by creating various different varieties of prompts and datasets. Finally, with the Gemini API Skill, learners can use the REST API or language-specific API SDK to generate text, create images, analyze content, and enhance applications with AI-driven features.
The course will take less than 2 hours to complete and Udacity recommends that learners already know intermediate Python before starting the Gemini API by Google course.
Want more AI Courses?
We have expanded our AI content catalog to almost 100 courses including Nanodegrees programs in subjects like Generative AI, AI Programming with Python, AI Product Manager, and many more. Learners can access the entire Udacity catalog with a single subscription. That’s 80+ Nanodegree programs, 350+ courses, 370+ real-world projects, and 2,500+ skills in the fields that are powering the digital future.
Get started with the free Gemini API by Google course today!