🚀🆕 New Lesson: Build Cloud Agents with Claude Managed Agents

⚓ The Short Version

Anthropic released Claude Managed Agents — a fully hosted agent runtime where Claude reads files, runs commands, browses the web, and executes code on its own. On their cloud. No servers for you to manage.

If you've ever built an AI agent, you know the real work isn't the agent logic — it's the infrastructure around it. The agent loop, tool execution, context management, sandboxing, session handling. All of that before a single line of real logic gets written.

Managed Agents moves all of that off your plate.

———

⚓ What Actually Changed

Two things shipped:

Claude Managed Agents — fully hosted agent harness. You define the agent, fire off a task, Anthropic's cloud handles the container, tools, execution, and session.
Claude Agent SDK — a Python/TypeScript library that embeds the same agent loop into your own infrastructure. Same power, you host it.

Both solve the same problem. The difference is where the agent runs.

———

⚓ Why This Matters for Us

The four building blocks are dead simple:

Agent — your config (model, system prompt, tools)
Environment — a cloud container with packages
Session — agent + environment running a task
Events — messages between your app and the agent

Create an agent once, spin up sessions whenever you need work done. Context compaction is automatic — the same system that powers Claude Code keeps your sessions alive when the context window fills up.

Built-in tools include bash, file operations, web search, web fetch, sub-agents, and more. Plus MCP server support for connecting external services.

———

⚓ The Lesson

I put together a full lesson in The Deep End classroom:

🏴‍☠️ Build Cloud Agents with Claude Managed Agents

What's in it:

The four building blocks explained in plain language
A complete working agent in under 20 lines of Python
How the agent loop works (with a real example)
Built-in tools, safety controls, and credential management
A copy-paste prompt you can drop into Claude Code to interrogate the lesson interactively
Links to the official Anthropic documentation

If you've been curious about building agents but didn't want to wire up all the infrastructure yourself — this is the on-ramp.

———

🗝️ Key Takeaways