Anthropic just dropped something massive. You can now tell Claude what you want an AI agent to do — and Anthropic builds it, runs it, manages it, and keeps it going. On their servers. Here's what it means and how to use it.
On April 8, 2026, Anthropic launched Claude Managed Agents in public beta. It's available right now through the Claude API.
Here's the short version: before this, if you wanted to build an AI agent — something that can work on its own, complete tasks, manage files, and talk to other tools — you had to build all of that yourself. The agent loop, the tool execution, the error handling, the infrastructure. That could take weeks and a lot of money.
Now, Anthropic handles all of it. You describe what you want the agent to do. They build, run, manage, and host it on their servers. If something breaks, it recovers automatically. If the task takes hours, it keeps going.
Think of it this way: before, you had to build the car, the road, and the gas station. Now Anthropic says “just tell us where you want to go.”
This is a big deal because AI agents went from something only engineers could build, to something founders with some technical skills could build, to — now — something anyone can spin up through an API call. The barrier just dropped dramatically.
Managed Agents are built on four concepts. Once you understand these, everything else clicks.
Agent
The blueprint. You define what model to use, what tools it has access to, and what its instructions are. Reusable — create once, run many times.
Environment
The workspace. A secure cloud container where the agent runs code, reads files, and accesses the internet. You control what it can and can't reach.
Session
A running instance. When you give an agent a task, it starts a session. The session keeps running until the task is done — even if it takes hours.
Events
The conversation. Messages between you and the agent — you send instructions, the agent sends back results, status updates, and questions.
Why This Architecture Matters
If the agent crashes, the session preserves its entire history. A new agent instance spins up, reads the session log, and picks up exactly where it left off. Your work is never lost. This is the “brain vs. hands” design — Anthropic decoupled the thinking from the doing so either can fail independently without killing the whole task.
Every Managed Agent comes with 8 built-in tools enabled by default. No setup required.
On top of these, you can add custom tools (your agent calls your code when it needs something specific) and MCP servers (connect to external services like databases, APIs, or internal tools using the Model Context Protocol).
What This Means in Practice
Your agent can research a topic online, write a report, save it as a PDF, process a spreadsheet, run a Python script to analyze data, fetch information from your company's internal API — all in a single session, all autonomously. It's not just answering questions. It's doing work.
You need a Claude API account. If you've never used the API before: go to console.anthropic.com, create an account, add a payment method, and grab your API key. That's it.
There are two ways to do this: the CLI tool (fastest) or API calls (more control). I'll show you both.
Option A: The CLI (Easiest)
Anthropic released a CLI tool called ant. On Mac, install it with: brew install anthropics/tap/ant. Then you can create agents, environments, and sessions from your terminal with simple commands.
Create an Agent. This is the blueprint — what model to use, what instructions to follow, and what tools it has access to. You define its name, system prompt (its personality and rules), and which Claude model it runs on. Available models: Claude Sonnet 4.6, Claude Opus 4.6, and anything Claude 4.5 or later.
Create an Environment. This is the secure container where the agent works. You can pre-install packages (Python libraries, npm packages, etc.), control network access (restrict which websites it can reach), and mount files it needs. Think of it as setting up a desk for your new employee.
Start a Session. Connect your agent to its environment and give it a task. The session starts, the agent begins working, and you receive real-time updates as events. The agent keeps going until the task is done or it needs your input.
Stream the results. You can watch what the agent is doing in real time through Server-Sent Events (SSE). You'll see its thinking, its tool calls, its results — everything. When it's done, it goes idle and waits for your next instruction.
Option B: API Calls (More Control)
If you prefer working directly with the API, it's three endpoints: POST /v1/agents (create), POST /v1/environments (workspace), POST /v1/sessions (run). Send events with POST /v1/sessions/{id}/events and stream responses with GET /v1/sessions/{id}/stream. SDKs are available in Python, TypeScript, Java, Go, C#, Ruby, and PHP.
Important
Managed Agents is currently in public beta. All API calls require the beta header: anthropic-beta: managed-agents-2026-04-01. If you use the official SDKs, this header is set automatically.
Data Processing
Upload a messy CSV, the agent cleans it, analyzes trends, builds charts, and delivers a summary report — all autonomously.
Research Agents
Give it a topic, it searches the web, reads sources, cross-references data, and writes a comprehensive brief with citations.
Code Generation
Describe a tool you need, the agent writes it, tests it, debugs it, and delivers working code — complete with documentation.
Content Pipelines
Feed it raw notes, it produces blog posts, social captions, email newsletters, and repurposed formats — in your voice.
Multi-Agent Teams
One agent coordinates others. A manager agent delegates research to one agent, writing to another, and review to a third.
Internal Tools
Connect to your company's APIs via MCP, let the agent query databases, update records, and generate reports on a schedule.
Two costs: tokens (what Claude thinks) and session time (how long the container runs).
| Cost | Amount |
|---|---|
| Sonnet 4.6 input | $3 per million tokens |
| Sonnet 4.6 output | $15 per million tokens |
| Opus 4.6 input | $5 per million tokens |
| Opus 4.6 output | $25 per million tokens |
| Session runtime | $0.08 per hour (metered to the millisecond) |
| Web searches | $10 per 1,000 searches |
Real-World Example
A 1-hour session using Opus 4.6 with ~50K input tokens and ~15K output tokens costs roughly $0.71 total. That's the agent thinking, working, using tools, and delivering results for less than a dollar. Session time only accrues while the agent is actively running — idle time and wait time are free.
Where does this fit in the Claude ecosystem? Here's the honest breakdown.
| Managed Agents | Claude API | Agent SDK | |
|---|---|---|---|
| Runs on | Anthropic's cloud | Your servers | Your machine |
| Agent loop | Pre-built, managed | You build it | Pre-built (local) |
| Tool execution | Managed containers | You implement | Local filesystem |
| Best for | Long-running async tasks, minimal infra | Custom loops, fine-grained control | CI/CD, local automation |
| State | Persistent sessions | Stateless per request | Session-based (local) |
| Recovery | Automatic | You handle it | You handle it |
Bottom Line
Use the regular Claude API if you want full control over every interaction. Use the Agent SDK if you want agents running on your own machines (great for CI/CD and local automation). Use Managed Agents if you want Anthropic to handle the infrastructure so you can focus on what the agent actually does.
AI agents started showing up less than a year ago. At first, only engineers could build them. Then it was technically-savvy founders. Now, Anthropic is saying: we'll handle the hard parts — you just tell us what the agent should do.
Every month, the barrier to entry gets lower. Every month, what agents can do gets more powerful. The people who start learning how agents work now — even at a basic level — will have an enormous advantage in 6 months when this technology is everywhere.
You don't need to be an engineer. You don't need to understand containers or API architecture. You need to understand what's possible and how to think about automation. That's the skill that transfers no matter which tool you use.
The gap between “person who uses AI” and “person who has AI working for them” is closing fast. Managed Agents just closed it further.
Managed Agents is a glimpse of where AI is going. But you don't need to wait for the future — you can build a complete AI operating system for your job right now with tools that already exist. That's exactly what the Weekend Claude Bootcamp does.
Claude connected to your email. Your calendar automated. Custom skills that handle your most repetitive tasks. Scheduled agents that work while you sleep. A complete system — built for your exact role — in one weekend.
25
Job-specific chapters
4
Phases per chapter
1
Weekend to complete
On Sale This Week Only
The people who understand AI agents now are the ones who won't be scrambling later. This is the lowest price the bootcamp will ever be.
Get the Bootcamp Now →© 2026 Mariah Brunner. All rights reserved.