Anthropic brings agentic plugins to Cowork
ThinkingNews Desk · how this was written
Anthropic has launched Cowork, an agentic tool that lets enterprise users customize Claude’s workflow with plugins for specific tools, data and commands, automating department-specific processes and improving team efficiency. Developers note that AI coding assistants such as Claude Code can build entire applications and fix bugs under human supervision, though a study found a notable performance gap in debugging tasks when using these tools.
Written from all 3 reports below, not from any single one.
How it was reported
- TechCrunch·Anthropic brings agentic plugins to Cowork
Anthropic introduces agentic plugins to Cowork, enabling customization of Claude's workflow. Users can specify tools, data, and commands to achieve consistent outcomes. This allows for tailored workflows and improved team efficiency.
- TechMeme·Anthropic expands its agentic plugins, which let enterprise users automate department-specific workflows, from Claude Code to its new general-use tool Cowork (Lucas Ropek/TechCrunch)
Anthropic has launched Cowork, a new agentic tool. It expands on the benefits of Claude Code, an AI coding assistant. Cowork automates department-specific workflows for enterprise users.
- Ars Technica·Developers say AI coding tools work—and that's precisely what worries them
Developers say AI coding tools like Anthropic's Claude Code and OpenAI's Codex work. These tools can build entire applications and fix bugs with human supervision. They are divided on whether this is good news, with some skeptical of marketing hype.
- TechMeme·Anthropic details an experiment on whether AI coding tools shape developer skills, finding that the biggest performance gap appears in debugging tasks (Anthropic)
Anthropic's experiment found a significant performance gap in debugging tasks when using AI coding tools. AI can speed up certain tasks by 80%. The study analyzed Claude.ai data to understand how AI impacts developer skills.
Related stories
- Anthropic debuts a Code Review feature for Claude Code, which uses agents working in teams to check pull requests for bugs, available in research preview (David Gewirtz/ZDNET)3 outlets
- Anthropic's Claude Opus 4.6 brings 1M token context and 'agent teams' to take on OpenAI's Codex7 outlets
- Anthropic ships major Claude Design overhaul with design system imports, code round-trips, and a fix for its token-burning problem3 outlets
- Anthropic announces an "auto mode" that enables Claude Code to make permission-level decisions while preventing destructive actions like mass file deletion (David Gewirtz/ZDNET)3 outlets