3 posts tagged with "AI Agent"

If you build with Claude, the important thing about Claude Managed Agents is not that Anthropic shipped “another agent feature.”

It is that Anthropic just moved one layer up the stack.

Instead of only selling model access and tool primitives, Anthropic is now selling a managed runtime for long-running agents: agent definition, cloud environment, sessions, event streaming, built-in tools, and the operational harness that keeps the whole thing alive.

That changes the developer conversation from:

• “How do I wire an agent loop together?”
• “How do I make it resumable, observable, and secure?”

to:

• “What should my agent actually do?”
• “Where do I want control, and where am I happy to let Anthropic own the infrastructure?”

The most important thing to get right about Conway is this:

Conway is not an officially launched Anthropic product.

What exists today is a mix of:

• official Anthropic launches around Cowork, Dispatch, computer use, scheduled tasks, and auto mode
• current help-center documentation that shows how those pieces now fit together
• an April 1, 2026 third-party report that surfaced an unreleased internal environment called Conway

If you only look at the leak, you miss the architecture. If you only look at the official launches, you miss where Anthropic seems to be going.

The technical story is the combination of both.

If you want Cowork to do real work for you, plugins are the lever.

As of February 28, 2026, we now have a clear official path:

• Anthropic introduced Cowork on January 14, 2026
• Custom plugin creation/sharing was announced on January 20, 2026
• Enterprise plugin directory updates shipped on February 24, 2026
• Plugin help docs were updated on February 25, 2026

This guide combines that official flow with practical lessons from community users so you can build your first useful plugin from scratch.