VS Code now offers an experimental feature called 'Rubber Duck' that lets developers request a second opinion from a different AI agent.
This helps catch mistakes that a single AI's self-review might miss.
It was previously in GitHub Copilot CLI and is now in VS Code.
What happened
Visual Studio Code 1.135 now includes an experimental 'Rubber Duck' feature that lets developers request a second opinion from a different AI agent, separate from the main coding assistant. It was first introduced in GitHub Copilot CLI in April 2026 and has now been adapted for VS Code.
Why it matters
The feature addresses a key limitation of AI-assisted development: when a single AI model reviews its own work, it tends to use the same biases and may miss errors. By using a different AI model for review, developers can catch mistakes earlier, reducing the need to redo planning or coding—saving time and effort.
What to watch
The feature is available via the '/rubber-duck' command in the Copilot Agent Host session within VS Code. It is part of a series of updates in VS Code 1.132 to 1.135, which also include a hybrid Markdown editor, a comment feature for web pages in the integrated browser, and automatic hot reload for local HTML files.
Ask the AI about this article →
The introduction of the Rubber Duck feature in VS Code comes from a practical need: AI agents often fall into the trap of self-review bias. When the same AI model plans and reviews its own implementation, it may overlook errors due to inherent biases. By tapping a separate AI agent for a second opinion, developers can increase the chances of catching problems early, saving time and reducing the rework that often follows late-stage failures. The feature's name is a nod to a classic debugging technique where programmers explain their code to a rubber duck to spot issues. This move is part of a broader trend in developer tools to improve AI reliability through multi-model collaboration. As these tools evolve, they may help reduce the trial-and-error that currently accompanies AI-assisted coding, though the effectiveness of cross-model reviews is still an area of active experimentation.
For example, today's edition would include:
AI-summarized, only the topics you pick — one digest a day via Email, Slack, or Discord.
Free · takes 30 seconds · unsubscribe anytimeWhat is AIToday? →
Ask AI anything about this article. Q&As are published on this page for other readers too.
CBTS Technology Solutions LLC launched Forge Agents, a platform that turns a plain-language job description in…
Imec CEO Patrick Vandenameele said at SEMICON Taiwan 2026 that the Belgian research center is broadening its c…
Alphabet's AI Overviews now reach over 2.5 billion monthly users through Google Search, and its ad business ge…
Amazon Web Services (AWS) has integrated its fully managed data warehouse service, Amazon Redshift, with Agent…
Anthropic is making a permanent 25% increase to the usage limits in Claude Code, effective after September 14
Sonos announced a new app update with generative AI features, a new soundbar called the Beam Ultra, and its se…
