Introducing Claude Managed Agents: everything you need to build and deploy agents at scale. It pairs an agent harness tuned for performance with production infrastructure, so you can go from prototype to launch in days. Now in public beta on the Claude Platform.

Shipping a production agent meant months of infrastructure work first. Managed Agents handles that for you. Define your agent's tasks, tools, and guardrails, and we run it on our infrastructure. Here's what early customers have built:

lets teams delegate work to Claude directly inside their workspace. Dozens of tasks run in parallel, and whole teams collaborate on the outputs. Available now in private alpha:

built AI Teammates on Managed Agents: agents that work inside Asana as part of your team, picking up assigned tasks. Offloading the infrastructure let them put engineering time into the multiplayer experience.

deploys specialist agents, powered by Managed Agents, for product, sales, marketing, and finance, each one in under a week:

now takes you from Seer's root-cause analysis to a Claude-powered agent that writes the fix and opens a PR. They built the integration on Managed Agents in weeks:

On @vibecodeapp_, developers can now spin up agent infrastructure at least 10x faster with Managed Agents, going from a prompt to a deployed app without weeks of setup:

Build and deploy your agents through the Claude Console, Claude Code, or our new CLI: Read more on the blog:

Life if anthropic just fixed the usage

This is all I have to say

Guys how am I supposed to use your tools to build things if yall build the things first 😂 😭

Claude dropping another massive update before we’ve even figured out the last one 😭

nice work can you also get Claude to work now?

its everyday

Againn

@lydiahallie Cool now let’s see who survives the usage limits long enough to actually deploy one !

We created the open source version of Claude Managed Agents.

Me after every claude update...

That's cool and all but your entire status page is orange right now. Shipping new products while Claude Code, Cowork, and the API are all showing Degraded Performance simultaneously is certainly a choice. 🙄

let me breathe mfker.

you guys rn 😂

They can’t stop

Finally realizing why Anthropic has been able to ship so fast since they have access to Mythos

Claude Mythos made this. That’s why they ship fast.

These guys don’t stop Mythos is carrying the team

@BladeWeb3

Don't forget to learn these AI courses from Claude as well. All for Free ↓ → Claude 101. Learn Claude for everyday work → AI Fluency: Frameworks & Foundations → Introduction to Agent Skills → Intro to Model Context Protocol

Just built my Oura Ring health agent on Managed Agents in minutes... the same setup took me DAYS on OpenClaw. First impressions and honest thoughts here 👇

Unfortunately, this is the part people underestimate Getting an agent to do something once is easy enough now, but getting it to run reliably with memory, retries, recovery, and guardrails is where the real product starts

Interesting! How’s your infrastructure gonna handle this? People seem to be complaining a lot recently because of usage limits

In life there are only two certainties: death and that Claude goes down the day something new is launched.

CONWAY! 🔥

Anthropic keeps moving up the stack. Opus helps you think. Claude Code helps you build. Managed Agents helps you assemble the whole thing. At this rate, what exactly is left for the rest of us to do?

WE WANT MORE USAGE FROM OUR MAX SUBSCRIPTIONS. NOT FEATURES THAT ARE GOING TO USE THOSE SUBSCRIPTIONS IN A FEW MINUTES!!?!?

Claude: "prototype to production in days" Me still debugging the same prompt for 3 days: 😭 Managed Agents just deleted the entire infra hell arc. Anthropic is speedrunning the agent economy while we're still in the tutorial. Now fix the rate limits so I can actually use it 😂 @claudeai

Anthropic just killed 1,000 startups

I’ll switch to Whip now… since you didn’t stop Claude.

gj claude