GitHub’s Tim Rogers showcases how developers can leverage Copilot Coding Agents to run complex code generation tasks in the cloud, highlighting new integrations and automation workflows.

Running Code Generation in the Background with GitHub Copilot Coding Agents

Presented by Tim Rogers, GitHub

GitHub Copilot Coding Agents have evolved to run in the cloud, allowing developers to offload complex code generation and automation tasks while continuing to work uninterrupted locally. This walkthrough covers:

Key Features

Delegating Complex Tasks

  • Offload operations like “add comprehensive tests” to Copilot agents running in the cloud
  • Continue coding as agents work in the background

Multiple Entry Points

  • Trigger Copilot Coding Agents from:
    • GitHub.com
    • Visual Studio Code
    • GitHub CLI

Model Selection and Customization

  • Choose which AI model powers your coding agents (e.g., Claude 3.5 Sonnet, Opus)
  • Model choice affects result quality and performance

Automation Use Cases

  • Automated code review
  • Security scanning
  • Performance optimization tasks

Copilot CLI Integrations

  • Handoff tasks from the cloud agent to your local workflow via CLI
  • Delegate work initiated locally to be executed in the cloud

Roadmap and Considerations

  • Upcoming features: more planning capabilities, enhanced privacy options, extended reporting tools
  • Privacy and performance optimization are a focus of ongoing development

Connect with GitHub

  • Twitter/X: https://twitter.com/github
  • LinkedIn: https://linkedin.com/company/github

This demo provides actionable insights for developers looking to automate development workflows and enhance productivity through cloud-powered AI coding agents.