News

VS Code Copilot Gets Closer to Tab, Tab, Tab Coding

Microsoft is previewing new AI tech that predicts your next edit, allowing devs to just Tab to accept it and keep on going.

It's the latest advancement to basically just saying: "Create a data-driven cloud app that ..." and just tabbing to go through the steps -- the ultimate in supercharged low-code/no-code constructs.

Called Copilot Next Edit Suggestions (Copilot NES), it's previewed in the new Visual Studio Code v1.97, the January 2025 update.

"Based on the edits you're making, Copilot NES both predicts the location of the next edit you'll want to make and what that edit should be," Microsoft said. "NES suggests future changes relevant to your current work, and you can simply Tab to quickly navigate and accept suggestions."

Microsoft described it as a natural evolution of autocomplete as most coding just edits existing code.

The following animated GIF shows how changing a variable triggers an edit suggestion further down the file so devs can just use the Tab key to navigate and accept the suggestion. The gutter indicator will guide next edit suggestions.

Copilot Edits in Animated Action
[Click on image for larger, animated GIF view.] Copilot Edits in Animated Action (source: Microsoft).

Speaking of edits, the company also moved Copilot Edits into general availability as it graduated from preview with the ability to apply natural language-driven code edits across multiple files, allowing developers to refactor, update, and modify code at scale with AI-assisted precision. Key features include:

  • Multi-File Editing: Developers can specify a set of files and instruct Copilot to implement changes across them, enhancing efficiency in large projects.
  • Natural Language Prompts: By providing instructions in everyday language, developers can guide Copilot to make specific code alterations, reducing the need for manual coding.
  • Inline Code Review: Copilot Edits offers an inline review experience, allowing users to preview proposed changes, accept or reject individual edits, and maintain control over code modifications.

"Edits can now be accepted and discarded individually, giving you more control," the dev team said. "Also new is that the editor controls for edits remain visible when switching to the side-by-side view. This is useful for understanding larger changes."

Other highlights of v1.97 include:

  • Reposition Command Palette: Users can now drag the Command Palette and Quick Input dialogs to a preferred position on the screen for enhanced accessibility.
  • Auto-Accept Edits: A new setting allows automatic acceptance of Copilot's suggestions after a configurable timeout, reducing manual confirmations.
  • Extension Publisher Trust: Enhancements have been made to maintain a secure environment by establishing trust with extension publishers.
  • Compound Logs: Developers can combine multiple logs into a single, aggregated view, simplifying debugging and monitoring.
  • Filter Output Logs: The Output panel now supports content filtering, enabling users to focus on relevant log information.
  • Git Blame Information: Rich Git blame details are now available, with direct links to view code on GitHub.
  • Search in Debug Variables: A new feature allows filtering and searching within debug variables to quickly locate specific values.
  • Notebook Inline Values: In notebooks, inline values for code cell variables are displayed, aiding in code comprehension and debugging.
  • Python No-Config Debugging: Developers can now quickly debug Python scripts or modules without prior configuration, expediting the development process.

About the Author

David Ramel is an editor and writer at Converge 360.

comments powered by Disqus

Featured

  • VS Code Copilot Gets Closer to Tab, Tab, Tab Coding

    Microsoft is previewing new AI tech that predicts next edits, allowing devs to just Tab to accept them and keep on going.

  • GitHub Previews Agentic AI in VS Code Copilot

    GitHub announced a raft of improvements to its Copilot AI in the Visual Studio Code editor, including a new "agent mode" in preview that lets developers use the AI technology to write code faster and more accurately.

  • Copilot Engineering in the Cloud with Azure and GitHub

    Who better to lead a full-day deep dive into this tech than two experts from GitHub, which introduced the original "AI pair programmer" and spawned the ubiquitous Copilot moniker?

  • Uno Platform Wants Microsoft to Improve .NET WebAssembly in Two Ways

    Uno Platform, a third-party dev tooling specialist that caters to .NET developers, published a report on the state of WebAssembly, addressing some shortcomings in the .NET implementation it would like to see Microsoft address.

  • Random Neighborhoods Regression Using C#

    Dr. James McCaffrey from Microsoft Research presents a complete end-to-end demonstration of the random neighborhoods regression technique, where the goal is to predict a single numeric value. Compared to other ML regression techniques, advantages are that it can handle both large and small datasets, and the results are highly interpretable.

Subscribe on YouTube

Upcoming Training Events