Tag
Google introduces Custom Agents in Antigravity 2.0 and CLI, a feature that enables specialized AI agents to improve coding productivity by reducing context bloat and allowing division of labor.
A thought leader argues that the immediate future of all AI agents is coding agents, which can solve general-purpose problems by writing code. He posits that TypeScript, with its security, portability, type-safety, and efficiency, is the ideal language for custom agent execution.
GitHub introduces custom agents in Copilot CLI, allowing developers to define specialized, reusable workflows in Markdown files for tasks like security audits and release notes.
Rhys Sullivan argues that companies should make their APIs, skills, and knowledge accessible to users' own AI agents rather than forcing everyone to use in-app agents, enabling power users to leverage their preferred models and local context while still offering simple interfaces for regular users.