Google is transforming the cloud with AI, for developers and regular users alike

Join top executives in San Francisco on July 11-12 to hear how leaders are integrating and optimizing AI investments for success.. Learn more

With all the AI ​​news going in and out (I/O, get it?) at today’s Google I/O conference, it’s easy to feel overwhelmed with how deeply generative AI is being integrated into Google’s portfolio. .

In summary, Google today announced its PaLM 2 large language model (LLM), which will have a dramatic transformative impact across all Google services. One area that is poised to get a big boost is the cloud. Google is deeply integrating generative AI into its cloud through a new interface that aims to help make developers and cloud users more productive. The interface, powered by a Google technology called AI Duouses the PaLM 2 model as a base.

The new AI-powered interface has an initial set of features including code assist capabilities to help developers write code for apps that run on Google Cloud. There is also a new generative AI chat support feature to help cloud developers find solutions to help build and deploy cloud applications. Rounding out the initial set of AI-powered features is AppSheet, a no-code solution that will allow any user to write cloud apps with natural language prompts.

“Duet AI for Google Cloud is really about adding an AI assistant to the cloud interface,” Richard Seroter, director of developer relations and outbound product management at Google Cloud, told VentureBeat. “Duet is a model based on PaLM 2, but we’ve extended and tuned it specifically with Google Cloud content.”


transform 2023

Join us in San Francisco on July 11-12, where top executives will share how they’ve integrated and optimized AI investments to achieve success and avoid common pitfalls.

Register now

How Duet AI could completely change the way the cloud is managed and developed

For both new and experienced cloud users, there can often be a lot of complexity, which can lead to confusion about how to execute certain types of operations.

Seroter joked that when people buy a new car, they usually just jump in and drive, without needing to read the car’s manual first. The cloud doesn’t work the same way in the sense that users typically need to read certain documentation, and there’s a lot of documentation to review.

The goal with Duet AI is to bring a conversational experience to learning how to better deploy code and manage applications in the cloud. So instead of a user scrolling through stack overflow answers, Google search results or YouTube videos, the user can simply ask a question and get an answer right in the cloud console.

“If I can extract good practices, including starting and improving expert practices, into a console chat, which can get me to some of the right places, I think it will be really powerful for people who are intimidated by this behemoth. powerful. , amazing cloud experience,” said Seroter.

Duet AI was trained on Google Cloud data to optimize deployment

The modern cloud consists of many different options that developers need to consider for application deployment, including different types of containers and virtual machines.

Seroter said that the complexity of cloud implementation is the reason Google had to tune Duet AI specifically with information about Google Cloud.

“So we found all of our documents, which is over a million pages of documents, not to mention every code sample we’ve ever written, every reference app, every blog post and every YouTube video transcript,” Seroter said.

Rather than just relying on generic information that PaLM 2 might have, Duet AI has the right context-specific information to provide accurate answers about Google Cloud.

The future of Duet AI in the cloud is ‘day two’ operations and SRE

The initial release of Duet AI for Google Cloud has a focus on developers, which will expand in the coming months to what are called “day two” operations, or continuous cloud management (in software development jargon, code development and deployment is generally referred to as a “day one” operation, with ongoing maintenance being “day two”).

Seroter said the future iteration of Duet AI for the Google Cloud will help organizations with site reliability engineering (SRE) and architecture-level best practices that keep cloud applications running on day two and beyond. . Going one step further, Seroter sees a future where Duet AI can also help with cloud cost optimization, to help organizations become more efficient with how they deploy and manage cloud infrastructure and applications. Cloud.

“AI is the new interface for the cloud,” Seroter said. “It’s not just about sitting outside of the cloud, this is infused into the cloud experience.”

VentureBeat’s mission is to be a digital public square for technical decision makers to gain insights into transformative business technology and transact. Discover our informative sessions.


Scroll to Top