GitHub is introducing custom agents for Copilot CLI—AI assistants that teams can define using Markdown files stored in a `.github/agents` directory. Each agent profile specifies the agent's role, which tools it can access, and guardrails that keep outputs consistent and safe.
Instead of one-off prompts, developers can now create specialized agents for repeated tasks (e.g., a security audit agent that runs standard checks and outputs a PR-ready checklist, or an IaC compliance agent that reviews infrastructure code against organizational policies). Because the agent profile lives in the repository, teams can review, version, and share it.
Custom agents work directly in the terminal via the `/agents` slash command in GitHub Copilot CLI, executing the same workflow consistently each time. The approach lets teams tailor Copilot CLI with expertise for specific development tasks without starting from scratch.
Summaries like this, in your inbox every morning.
Pick your industry and the AI tools you use, and get news related to your work every day.
Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →
Ask AI anything about this article. The AI reads this article, earlier AIToday articles, and Wikipedia, and cites its sources. Q&As are published on this page for other readers too.
Aparna Nair, IBM's chief talent, leadership, and culture officer, said generalists alone "will cut it" in the…
Vinci4D provides chip-design simulation software that trains on physics equations instead of customer data, an…
Reflection AI introduced Beam, an open-weight model for agentic coding and long-horizon tasks, with 501 billio…
After finishing his first series, the author ran five sub-agent reviews and got back findings including five c…
An e-dash SRE used Claude Code with a Chrome extension for about three months on a low-code admin console with…
A script that ran fine by hand failed unattended with UnicodeEncodeError, because the console's encoding was c…
