Tech
Programmers, do you get window-switch whiplash? Google's new Code Assist aims to help
When we last visited Gemini Code Assist back in April, the product was in pre-release. Code Assist ran using Gemini 1.5. Now it’s been released and updated to what Google (we haven’t tried it yet) says is the much more capable Gemini 2.0.
Today, Google is announcing Gemini Code Assist tools, which Ryan J. Salva, senior director, product management, and Prithpal Bhogill, group product manager, describe in today’s blog post as a “connected development ecosystem.”
Also: The most popular programming languages in 2024
They also describe Code Assist tools as “a paradigm shift in how developers get the information they need to build and manage apps.”
Hmm… David’s First Rule of Technology Marketing is if a product manager loves how you describe a benefit, don’t use it in your marketing copy. The corollary to David’s First Rule is that if your engineers like how the product is described, so will your tech customers.
Product managers just love calling their products “paradigm shifts.”
To be fair, this product involves a combination of generative AI and Google, and we’ve been experiencing paradigm shifts on an almost daily basis. The pace of change is enough to make you dizzy. But this reality also means we can’t just immediately discount Salva and Bhogill’s marketing as hyperbole.
So, let’s explore what Code Assist tools offer, and you can judge whether today’s “paradigm shift” is hyperbolic or game-changing.
Gemini Code Assist is a code helper that lives inside your development environment, like VS Code or Jetbrains. While you edit code, you can type a prompt and get a response from Code Assist.
Also: 25 AI tips to boost your programming productivity with ChatGPT
What Salva and Bhogill are announcing today is the integration of third-party tools into Code Assist so you can use those tools from your editing environment. The idea is that programmers won’t have to switch to a new window to get to their tools — what they’ll need is literally at the end of a keypress.
Right now, Google is announcing integration with the following tools in a private preview:
- GitHub: Everyone’s favorite source code control resource
- GitLab: Kind of like GitHub on steroids, for DevOps
- Google Docs: Access-controlled insight based on your docs
- Sentry.io: Dynamic metrics and debugging tool
- Atlassian (Rovo): Interactive AI access to corporate knowledge
- Synk: Security management tool for developing safe code
According to Danny Allan, CTO at Snyk: “By collaborating with Google Cloud to build a dedicated Gemini tool, we’re empowering developers to use Gemini to write code and Snyk to test and fix it — all within their IDE.”
Also: Google’s Gemini 2.0 AI promises to be faster and smarter via agentic advances
Allan talks about how staying in the interactive development environment (IDE) can help developers concentrate and maintain focus while coding: “This integration ensures developers can stay in their creative flow, leveraging AI to accelerate innovation while maintaining the highest standards of security.”
Tools like the ones in the list above can help developers achieve that goal. That said, I’m hard-pressed to see why GitHub is included because almost every IDE has tight integration with GitHub out of the box. Perhaps as Google expands its private preview, we’ll see what AI features apply to the GitHub integration.
Also: The best AI for coding in 2024 (and what not to use)
Salva and Bhogill say: “Getting scalable, secure applications into production requires more than just writing great code — developers need solutions for productivity, observability, security, databases, and more.”
Google is making sure this announcement is a partner business development pitch as much as it is a tool for developers. The company’s two product marketing professionals point to benefits like fostering direct developer connections and expanding reach that provide “opportunities for growth and engagement.”
The dual benefits statements reflect that powerful external development tools inside the IDE will improve programmer productivity. However, including those tools in the Google Code Assists offering will “extend their reach and brand awareness within the developer community.”
Google also promises to “proactively co-market with our partners to maximize exposure and tell a cohesive story.”
Also: 5 reasons why Google’s Trillium could transform AI and cloud computing – and 2 obstacles
Gemini Code Assist pricing starts at $19 per user per month for the standard service when purchased for an entire year.
The enterprise version starts at $45 per user per month when purchased for an entire year. The enterprise version provides codebase awareness for an entire-ish codebase. For an analysis of the limits of those versions, check out my article.
The tools add-on for Gemini Code Assist is in private preview, but you can click here to fill out a form and request access.
What do you think? Has Google achieved a “paradigm shift” with Gemini Code Assist tools? Do you use Code Assist or any other AI while programming? Let us know in the comments below.
You can follow my day-to-day project updates on social media. Be sure to subscribe to my weekly update newsletter, and follow me on Twitter/X at @DavidGewirtz, on Facebook at Facebook.com/DavidGewirtz, on Instagram at Instagram.com/DavidGewirtz, and on YouTube at YouTube.com/DavidGewirtzTV.