Google is upgrading its Code Assist programming agent to Gemini 2.0, adding source integrations

Following the launch of new generative AI models, Google He updated his code helpers to work with it Gemini 2.0 And expand the external data sources it connects to.

Code Assist will now run on the recently released Gemini 2.0, providing a greater context window for understanding larger enterprise codebases.

Google will also launch Gemini Code Assist tools in a special preview. The platform will connect to data sources such as GitLab, GitHub, Google Docs, Sentry.io, Atlassian, and Snyk. This will allow other developers and programmers to request help from Code Assist directly in their IDE. Previously, Code Assist was connected to VS Code and JetBrains.

The idea is to allow programmers to add more context to their work without interrupting their flow, Ryan J. Salva, senior director of product management at Google Cloud, told VentureBeat in an interview. Salva said Google will add more partners in the future.

Previously Duet AI, it was Code Assist It was launched for businesses in October. As organizations seek ways to simplify programming projects, demand for AI programming platforms like GitHub Copilot has increased. Code Assist added enterprise-level security and legal compensation with the release of the enterprise option.

Artificial Intelligence is where developers work

Linking Code Assist to other tools developers use provides more context for their work without having to have multiple windows open at once, Salva said.

“There are many other tools that a developer uses throughout the day,” Salva said. “They might be using GitHub or Atlassian Jira or DataDog or Snyk or all of these other tools. What we wanted to do was enable developers to bring that extra context into their IDE.”

Developers just need to open the Code Assist chat window and ask them to summarize the latest comments for specific issues or the latest pull requests on repositories, Salva said, “so they query the data source and bring the context back to the IDE, (and) the big language model can synthesize it.”

AI code assistants were one of the first important use cases for generative AI, especially after software developers began using ChatGPT to assist with programming. Since then, a large number of enterprise-focused programming assistants have been released. GitHub has released Copilot Enterprise In February, and oracle I fired her Java and SQL coding helper. Harness I came up with a coding helper built using Gemini Gives real time suggestions.

Meanwhile, OpenAI Anthropic has begun offering interface features that allow programmers to work directly on their chat platforms. ChatGPT canvas It allows users to create and edit code without copying and pasting it elsewhere. OpenAI too Added integration to tools Such as VS Code, XCode, Terminal, and iTerm 2 from the ChatGPT MacOS desktop application. Meanwhile, Anthropic Fired Antiques by Claude So Claude users can create, edit and run code.

Not Jules

Although Code Assist now supports Gemini 2.0, it remains complete, Salva noted Separate from Julesthe programming tool announced by Google during the launch of the new Gemini models.

“Jules is actually one of many experiments that the Google Labs team has come up with to show how we can use autonomous or semi-autonomous agents to automate the coding process,” Salva said. “You can expect that over time, experiments that graduate from Google Labs, with the same capabilities, may become part of products like Gemini Code Assist.”

He added that his team works closely with Jules’ team and is excited to see the progress Jules makes, but Code Assist remains the only generally available enterprise-level programming tool supported by Gemini.

Early feedback from Code Assist and Jules users shows strong interest in latency improvements in Gemini 2.0, Salva said.

“When you’re sitting there trying to code and trying to stay in the flow, you want these kinds of split-second responses to come out. Any moment that developers feel like they’re waiting on the tool is a bad thing, so we’re getting faster and faster responses from it,” he said. .

Coding assistants will still play a crucial role in the growth of the field of generative AI, but Salva said the next few years could see a change in how companies develop code-generating models and applications.

Already pointed out State of DevOps Acceleration Report 2024 From the DevOps research and evaluation team at Google, which showed that 39% of respondents do not trust AI-generated code and a decline in the quality of documentation and delivery.

“We as an industry have largely focused on improving productivity productivity and improving speed over the last four years,” Salva said. “And while we’re starting to see that correlate to a decline in overall stability, I think here the conversation in the coming year will really shift to how we can use AI to improve quality across multiple dimensions.”

Daily insights into business use cases with VB Daily

If you want to impress your boss, VB Daily has you covered. We give you the inside scoop on what companies are doing with generative AI, from organizational transformations to hands-on deployments, so you can share insights to maximize ROI.

Read our privacy policy

Thanks for subscribing. Check more VB Newsletters are here.

An error occurred.