The harness is all you need (mostly)
GitHub technologist Burke Holland argues that mastering the existing features of GitHub Copilot—the 'harness'—is more effective than chasing new AI tools or prompts. He recommends starting with the Gi…
GitHub technologist Burke Holland argues that mastering the existing features of GitHub Copilot—the 'harness'—is more effective than chasing new AI tools or prompts. He recommends starting with the Gi…
GitHub announced that enterprise managed settings now govern the GitHub Copilot app and Copilot cloud agent, allowing enterprise owners to define a single set of guardrails—such as plugin approvals an…
GitHub has launched the GitHub Copilot app, a workspace designed to manage multiple AI agent sessions across development workflows. The app allows users to connect agent sessions to specific projects,…
Anthropic's Claude Opus 5, its newest Opus model designed for complex, multi-step coding tasks, is now available in GitHub Copilot for Copilot Pro+, Max, Business, and Enterprise users across multiple…
GitHub has made its Copilot cloud agent for Linear generally available, allowing users to assign Linear issues to the autonomous background agent. The agent analyzes issues, opens draft pull requests,…
GitHub MCP Server now supports the next MCP specification ahead of its official release on 28th July 2026, which transitions the protocol to a stateless core for easier scaling. The server removed Red…
GitHub Mobile now lets users fix failing Actions checks with a Copilot cloud agent. From a failed check, selecting "Fix with Copilot" opens a new pull request that analyzes the issue and implements a …
GitHub has released agent automation controls in GitHub Issues in public preview, adding approvals, confidence ratings, and rationale for automated changes to labels, fields, type, close, and assignee…
GitHub Copilot and raw API access serve different needs: Copilot bundles development tooling—editor, repository, terminal, and organization policy integrations—with model access, while raw APIs are fo…
GitHub released a new Copilot usage metrics impact dashboard for enterprise administrators and organization owners, grouping engaged users by AI adoption phase (Phase 1 Code-first, Phase 2 Agent-first…
GitHub has introduced canvas extensions in the GitHub Copilot app, allowing developers to create interactive visual interfaces for tasks like issue triage, codebase visualization, and session manageme…
Google's Gemini 3.6 Flash model is now rolling out in GitHub Copilot, offering improved task-completion rates and token efficiency over Gemini 3.5 Flash for coding and agentic workflows. The model, bi…
GitHub now lets Copilot Business and Copilot Enterprise customers on GitHub Enterprise Cloud manage AI credit pools for cost centers directly in the billing UI, a feature previously restricted to the …
GitHub announced that Copilot Business and Copilot Enterprise users can now view the total AI credits used per billing cycle on their GitHub Copilot usage page, even without an individual budget. Prev…
GitHub Code Quality is now generally available on GitHub Enterprise Cloud and GitHub Team, offering deterministic CodeQL analysis and AI-assisted detection to catch maintainability and reliability iss…
GitHub has made repository-level Copilot usage metrics generally available via two new REST API endpoints, enabling enterprise and organization users to view daily, per-repository breakdowns of pull r…
GitHub's Copilot usage metrics API now reports GitHub Copilot app activity in enterprise and organization 1-day and 28-day reports, adding fields for daily active app users and a dedicated totals sect…
GitHub announced that Copilot code review now reads custom instructions from the head branch of pull requests, supports additional instruction files (REVIEW.md, GEMINI.md, CLAUDE.md), and allows custo…
GitHub Mobile now lets users select 'Fix with Copilot' directly from pull request comments, using a Copilot cloud agent to generate fixes without manual prompting. The feature is available on the late…
GitHub software engineer Dalia Abuadas argues that AI agents have made code generation cheap, shifting the expensive part of software changes from writing code to debating scope. She proposes using AI…