Brad Abrams

Product @ Anthropic

[ClaudeDevs @ClaudeDevs]

We’ve added a new way to access Claude on Google Cloud.

You can now use the full Claude API from your Google Cloud account, including Claude Managed Agents, code execution, Opus 5.5 fast mode, and new features as they launch.

[CJ Avilla @cjav_dev]

Seeing lots of struggles with API keys.

Started using WIF in more places recently so wanted to share in case this helps: https://t.co/CmuqAIweus

[Brad Abrams @brada]

Do you know what your agents did last night?
New cookbook: point Claude at your agent transcripts and it flags the sessions worth a second look. Works for CMA, Agent SDK and your own agent transcripts
https://t.co/CTAiVkIiVX

[Brad Abrams @brada]

I built a set of strategies with dynamic workflow for Claude Managed Agents: Advise, Grade, Fan-out, dream.
https://t.co/4uJWBIZDk5
What other patterns would you like too see?

[Brad Abrams @brada]

Take your data to the tools you love!

[ClaudeDevs @ClaudeDevs]

Now in public beta, Claude Platform can send OpenTelemetry traces from the Messages API, Claude Managed Agents, and the Claude SDKs to your observability stack.

[Brad Abrams @brada]

Building secure cloud-hosted agents for models this smart and persistent is not a weekend project.

We’ve put that work into Claude Managed Agents. For example, your API keys stay in a vault and the sandbox only ever sees a placeholder.

We just published a guide to locking down a deployment. https://t.co/CjuY2rx4Il

How confident are you in your agent sandbox?

[Michael Cohen @_hi_mc]

Fantastic writeup here on Flows and why we're all so excited about it:
https://t.co/73hucaO8QC

[CJ Avilla @cjav_dev]

You can kick the tires with Claude Managed Agent Duynamic workflows, today!

Checkout the Claude Console (https://t.co/tCUhnRkxst) and try out one of the templates with "Dynamic workflow" in the card.

[Harrison Stall @HarrisonStall]

big morning in NYC today talking about flows! what a blast, pumped for everyone to try things out. let us know what wild problems you’re able to solve with the platform!

[Brad Abrams @brada]

@Dandi_Ai Yes, that's the next step. Steer in chat while you're figuring out what works. Once a rule earns its keep, move it to the agent's system prompt. It's versioned, so every new session starts with it and your team can read and diff it.

[Brad Abrams @brada]

This was such fun to work on! Turn it on with one field on your agent, then ask for a workflow in a new session.

[ClaudeDevs @ClaudeDevs]

Claude Managed Agents dynamic workflows are now available in public beta. It's a new type of multiagent orchestration, built for your most ambitious workloads.

A lead agent writes a plan that runs across many agents in phases, combining the results at the end.

[Dan McAteer @daniel_mac8]

I pointed the new Claude Managed Agents dynamic workflows at 18k lines of code.

> 21 proven bugs.
> 5 minutes.
> $8.36, on my Claude Max API credits.

A lead agent writes a plan, runs it across many agents in phases, then merges the results.

Try it in Claude Code:

/claude-api managed-agents-onboard bug-hunter

It burns tokens fast. It's worth it.

[Michael Cohen @_hi_mc]

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!

[Brad Abrams @brada]

Tip 5: Two quick ways to start:
In the Console, pick a quickstart template and try it in a test session.

In Claude Code, type /claude-api managed-agents-onboard and it walks you through the setup.
Docs: https://t.co/CaLESVEmHr
Can't wait to see what you build!

[Brad Abrams @brada]

Tip 3: Curious what your agent built? Ask it. I asked mine to show me the workflow it wrote, and to draw the run.
"Print the workflow that you started the run with, word for word, in one code block. Do not start another run. Draw the workflow run as a diagram and save it to workflow-diagram.png, 1600x900, light background: phases left to right, one box per agent, arrows for what feeds what. Do it yourself; start no workflow run."

[Brad Abrams @brada]

Tip 2: Watch it work in the Console: each workflow run with its phases, a thread for every agent, and your spend against the budget.

[Brad Abrams @brada]

Tip 1: Set a budget and you'll experiment more freely. It's a dollar limit on the whole session, every agent included. Reach it and new work stops: the run pauses and keeps its work; raise it to resume.

[Priyanka @PriyankaPhatak]

If you're on a Max or Team plan you now get free API Credits. Use these credits to build your very first Claude Managed Agent. Here is an example implementation that walks you through building your first agent, a daily brief agent that keeps running autonomously, on a schedule that you set.

Try this out or your own ideas! But definitely use those free credits to give us a whirl!