Working on APIs for Claude Managed Agents @AnthropicAI. Probably wrong a bunch. Views are my own.
New York City, NY
Joined May 2025
- Tweets239
- Following214
- Followers5.9K
- Likes628
Fantastic writeup here on Flows and why we're all so excited about it:
latent.space/p/claude-dynami…
Michael Cohen retweeted
before I joined Anthropic, I spent about 2 weeks hacking on this as a side project with Opus 4. It used the Agent SDK so it needed a constantly running process & didnt work that well
but one prompt to Opus 5.5 ported it to Claude Managed Agents & made it way more reliable
you now get Claude API credits with your MAX plans ($100, or 200 matching your plan) every month, use this to build more personal AI for yourself!
I made an AI homepage that's generated everyday based on sites I read and replaces my 'new tab' page in Chrome
Michael Cohen retweeted
Here's the docs for dynamic workflows for Claude Managed Agents: platform.claude.com/docs/en/…
This was a labor of love from so many people and I'm so excited to see it out for everyone.
Dynamic Workflows are one of the most powerful capabilities you can utilize for uplift on your agentic workloads. Time and time again we've seen that letting Claude stitch together agents, context, and data programmatically leads to better outcomes. It also keeps your "Big Claude" free to talk to the user and orchestrate "lil Claudes", instead of spending time micromanaging individual threads.
This first release is only the beginning for Dynamic Workflows in CMA. We're going to invest a ton in giving developers more control and capabilities when working with workflows, and generally making the harness even more powerful, reliable, and flexible.
Massive shoutout to @karbon0x who was the mastermind behind Workflows for Claude Managed Agents.
Have fun Flowin' ya'll. Let us know what you think!
Michael Cohen retweeted
hung out with my very ai-pilled friend @danshipper to chat about how he built the Every agent on Claude Managed Agents. some cool tips in here on how they create benchmarks (can an agent edit copy as well as their team’s human editor?) to pull off continuous improvement
Michael Cohen retweeted
We’re rolling out monthly Claude Platform API credits for Max and Team plans:
Max 5x: $100
Max 20x: $200
Team: up to $500, pooled
Works on any model, including Haiku 5.5, in your code or third-party harnesses.
How it works and full terms: support.claude.com/en/articl…
It's just Claude all the way down!
I don't work on our Apps but I just wanted to express a ton of love and appreciation for the folks that do. Over the last few months the improvements made all across claude.ai and the desktop app have been super incredible to see. It's really a very fun time to spend hours on there now
Today, we are merging Claude Cowork and chat to simplify how you use Claude!
We are also integrating Claude Design so that you can ask Claude to make a Slide, Design, or Doc without needing to switch tabs or apps.
Many of you shared that you didn't want to choose which Claude product to use for any task. As Claude models have become more capable, we've found that Claude can handle the routing for you. Based on your prompt, Claude will decide whether to give a quick answer or do deeper agentic work, and what kind of output best fits the task.
You're in control the whole time: you can still stop, redirect, or exert finer control over Claude's effort or approach.
Give it a try and let us know what you think. We're rolling this out slowly over the next few weeks to get it right.
Michael Cohen retweeted
Watch our very own @RLanceMartin talk to founders of Actively, Pendo and Wispr on how they built on Claude Managed Agents youtube.com/watch?v=hm8NzEd5…
Michael Cohen retweeted
We've added `ant apply` to the ant CLI.
Now you can declare Claude Managed Agent environments, agents, skills, memory stores, and deployments as files in your repository and keep the API's resources in sync with them using `ant apply`.
Docs: platform.claude.com/docs/en/…
Michael Cohen retweeted
our goal with this release was to make increased intelligence safely accessible to as many builders as possible.
we did our best to balance dev experience, costs, and safety, all while scaling the Platform to support it.
there’s no way we got it all perfectly right, which is why we need your feedback. let us know what you love and what we need to do better.
Claude Fable 5.1 is available everywhere today. Claude Mythos 5.1, our model for cyberdefenders and life scientists, is available through trusted access programs.
Read more: anthropic.com/claude-fable-a…
Devs 🤝 Devs
Chat SDK can now run Claude Managed Agents.
A few lines of code delivers your agent to Slack, WhatsApp, Discord, Teams, and 30+ other apps.
vercel.com/changelog/claude-…
Michael Cohen retweeted
claude.com/customers/notion-… check out our one of our favorite customers @NotionHQ built with Claude Managed Agents
Michael Cohen retweeted
are you spending your time reinventing solutions to solved problems or are you spending your time inventing solutions to unsolved problems?
Michael Cohen retweeted
🎉Excited for our collaboration with @AnthropicAI
Claude Managed Agents & Agents SDK are now
AG-UI compatible!
Build Fullstack agent apps with:
- Generative UI
- Shared state
- Streaming chat
Connect your agents to Slack and MS Teams with the Channels SDK, and bring them seamlessly into OpenBot.
Check out the cookbook 👇
Claude Managed Agents can power many different UIs.
Our new cookbook pairs Claude Managed Agents with AG-UI, @CopilotKit's open Agent-User Interaction Protocol.
Michael Cohen retweeted
Claude Managed Agents for the backend.
CopilotKit for the frontend.
AG-UI in between 🤝
Michael Cohen retweeted
Claude Managed Agents 初めて触りましたが、用意していただいた資料がとても丁寧でわかりやすく、サクサク進められて楽しかったです🙌
Claude をもっと使いこなせるようになりたい🔥
クレジットまでいただけたので、しっかりアウトプットにつなげられるよう頑張るぞ💪
#ClaudeCommunityOsaka
that's a whollleeeeee lotta agents
In a new blog post, we share how one customer, ABC Legal, deployed Claude Managed Agents.
The fleet of 50+ agents have cut costs by up to 50% for certain legal tasks.
The agents also use a feedback loop to improve continuously over time.
Read more:
claude.com/blog/how-abc-lega…
