GitHub Copilot can now drive your browser: browser use enters public preview

GitHub Copilot browser use lets an AI coding agent control Chrome to debug web apps and run browser tests. It is in public preview across the CLI, the Copilot app, VS Code and JetBrains.

On 17 November 2026 GitHub announced browser use for GitHub Copilot in public preview. With the GitHub Copilot Chrome extension installed, Copilot can control your browser to debug a web app, automate browser tests and handle web tasks that need real clicking and typing.

What the changelog says

The pattern

This follows Anthropic’s Claude Code in-app browser work and Cloudflare’s agent-native browser, both of which we covered earlier. AI coding tools are moving from writing code to using the running product to check it. That is the step that has historically needed a human tester.

Why it matters to buyers

An agent that can click through your app finds a different class of bug: a broken sign-up flow, a button that does nothing on mobile width. It does not replace a tester who understands your customers, and giving an agent a logged-in browser is a permissions decision someone must own.

So what

When a supplier says they use AI to test, ask what the agent can see, which accounts it is signed into and who reviews the results. Our AI-assisted development work keeps a person accountable for those answers. To scope a build, start a project.

← All research

More research.

GitHub Copilot adds Supabase, Webflow, Wix and five more connectors in public preview

GitHub Copilot now connects to eight more services, including Supabase, Webflow, Wix and Mixpanel, through verified MCP connectors in public preview. They join more than 25 existing ones.

Read ›

Gemini 4 Neon is generally available in GitHub Copilot, aimed at lower-cost agentic coding

Gemini 4 Neon is now generally available in GitHub Copilot for agentic coding. Google says its quality is close to Gemini 4 Carbon at a lower token cost per task.

Read ›

Claude Code 2.1.328 brings auto mode to Bedrock, Vertex and Foundry, and narrows /code-review to bugs

Claude Code 2.1.328 extends auto mode to Claude Opus 4.6 and Sonnet 4.6 on Amazon Bedrock, Google Cloud and Microsoft Foundry. /code-review now reports only bugs and CLAUDE.md violations.

Read ›

GitHub Copilot Evals: repeatable tests for AI agents, now in public preview

GitHub Copilot Evals lets teams write repeatable tests for AI coding skills, custom agents and MCP tools. It checks both the result and the path the agent took, and is in public preview.

Read ›

Claude Code 2.1.327 refuses some symbolic links and lists broken setup in /status

Claude Code 2.1.327 tightens file and package permissions again and adds a /status list of broken agent, skill and hook settings. A short read for teams using AI coding tools on a live product.

Read ›

VS Code retires the Copilot Local harness in February 2027

GitHub will remove the older Local harness for Copilot agent sessions in VS Code in February 2027. Teams using AI coding agents need to move to the Copilot harness before then.

Read ›

Start a project

Building with AI? Let's talk.

Tell us what you are building. We'll give you an honest view of the right approach.

Start a projectSee our work