News

Microsoft Duels JetBrains with Same-Day AI Coding Moves

In an IDE AI update, this week we see JetBrains unveiling a new coding agent called Junie just as Microsoft introduced a free tier for GitHub Copilot in Visual Studio.

The moves are the latest efforts to expand the reach of coding AI, as GitHub just last month announced a free Copilot tier for Visual Studio Code that also applied to otheier IDEs, including JetBrains and even Visual Studio. So this week's post from Microsoft just follows up on previous news. Junie, though, is brand-new and waitlisted.

"With the launch of Junie, JetBrains AI coding agent, we are redefining how we code by leveraging its agentic power for co-creation right in your IDE," said Andrew Zakonov of JetBrains in a blog post yesterday. "With Junie, you can fully delegate routine tasks to your very own personal coding agent or collaborate with it to execute more complex ones together. Thanks to the power of JetBrains IDEs, coupled with reliable LLMs, Junie already solves tasks that would otherwise require hours of work."

Meanwhile, in a Microsoft post on the same day, Microsoft's Rhea Patel followed up on the original free Copilot announcement she made last month, in which she hinted at "putting the finishing touches on a more streamlined experience in January."

That more polished experience is now here.

"We're excited to announce an all new free plan for GitHub Copilot, available for everyone today in Visual Studio. All you need is a GitHub account. No trial. No subscription. No credit card," she said.

She again noted the limitations of the free tier:

Copilot Plans
[Click on image for larger view.] Copilot Plans (source: GitHub).

In addition to nothing the limitations, she highlighted features including advanced AI model access, new productivity-enhancing features (multi-file edits, enhanced chat, commit messages, debugging tools), and more.

JetBrains, meanwhile has set up an early access program waiting list for Junie, which is available for IntelliJ IDEA, PyCharm, WebStorm, GoLand, CLion, Rider, and DataGrip.

Key highlights of this new offering include:

  • Agentic Capabilities for Task Delegation: Developers can fully delegate routine tasks to Junie or pair with it on more complex ones, leveraging its agentic power for co-creation within the IDE.
  • Task Success Rate: According to SWEBench Verified, a curated benchmark of 500 developer tasks, Junie can solve 53.6% of tasks on a single run, indicating its potential to handle a wide range of development tasks efficiently.
  • Enhanced Code Quality: By combining the capabilities of JetBrains IDEs with large language models (LLMs), Junie not only accelerates development but also aims to improve code quality. It can generate code, run inspections, write tests, and verify their success.
  • Contextual Understanding and Adaptability: Junie is designed to understand the context of any given project and adapt to a developer's coding style. It can follow specific coding guidelines, ensuring that its contributions align with the team's standards.
  • Developer Control and Transparency: Despite its autonomous capabilities, Junie ensures that developers remain in control. Users can review proposed changes and guide critical decisions, maintaining oversight of the codebase.

About the Author

David Ramel is an editor and writer at Converge 360.

comments powered by Disqus

Featured

  • Mastering Blazor Authentication and Authorization

    At the Visual Studio Live! @ Microsoft HQ developer conference set for August, Rockford Lhotka will explain the ins and outs of authentication across Blazor Server, WebAssembly, and .NET MAUI Hybrid apps, and show how to use identity and claims to customize application behavior through fine-grained authorization.

  • Linear Support Vector Regression from Scratch Using C# with Evolutionary Training

    Dr. James McCaffrey from Microsoft Research presents a complete end-to-end demonstration of the linear support vector regression (linear SVR) technique, where the goal is to predict a single numeric value. A linear SVR model uses an unusual error/loss function and cannot be trained using standard simple techniques, and so evolutionary optimization training is used.

  • Low-Code Report Says AI Will Enhance, Not Replace DIY Dev Tools

    Along with replacing software developers and possibly killing humanity, advanced AI is seen by many as a death knell for the do-it-yourself, low-code/no-code tooling industry, but a new report belies that notion.

  • Vibe Coding with Latest Visual Studio Preview

    Microsoft's latest Visual Studio preview facilitates "vibe coding," where developers mainly use GitHub Copilot AI to do all the programming in accordance with spoken or typed instructions.

  • Steve Sanderson Previews AI App Dev: Small Models, Agents and a Blazor Voice Assistant

    Blazor creator Steve Sanderson presented a keynote at the recent NDC London 2025 conference where he previewed the future of .NET application development with smaller AI models and autonomous agents, along with showcasing a new Blazor voice assistant project demonstrating cutting-edge functionality.

Subscribe on YouTube