Jess Yan (@jess__yan) profile picture

PM @anthropicai building Claude Managed Agents. Ex-@stripe

Seattle, WA
Joined April 2026
Photo by Jess Yan (@jess__yan)
Jess Yan retweeted
You can now run Claude Managed Agents in your own cloud or data center: the harness, sandboxes, credentials, and session history. Model requests go to Anthropic, a supported cloud provider, or your own gateway. In private beta.
Self-hosted Claude Managed Agents is now in private beta. You can host the agent harness, sandboxes, and session history, in your own cloud or on-premises, and choose where requests to Claude are sent.
9
20
232
29,798
Claude Managed Agents -- with maximum deployment flexibility and infra modularity.
Self-hosted Claude Managed Agents is now in private beta. You can host the agent harness, sandboxes, and session history, in your own cloud or on-premises, and choose where requests to Claude are sent.
1
14
660
OTel is here!! Meeting you where you are 🤝
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.
1
2
12
634
Jess Yan retweeted
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.
428
726
287
12,531
1,048,235
Jess Yan retweeted
Two fresh updates to Claude Managed Agents: First, we've added a session viewer to the ant CLI. `ant beta:sessions connect` attaches your terminal to a running session, and `--web` opens a web UI served from localhost.
88
85
16
1,427
207,918
Jess Yan retweeted
We sat down with the founders of @WisprFlow, @useactively, and @pendoio, who are building on Claude Managed Agents. Learn how they used features like outcomes, sandboxing, and memory to scale their products.
78
52
17
1,239
164,689
Jess Yan retweeted
We shipped three updates to Claude Managed Agents. First, we made it easier to use memory with Self-Hosted Sandboxes. Any work done in a Self-Hosted Sandbox can be saved to memory.
125
164
40
2,972
332,414
This is one of my favorite use cases and deployments of Claude Managed Agents. Non-technical teams building custom agents and scaling them within their organization - proving that everyone is a developer now, given the right platform and tools. Great work by @abclegal!claude.com/blog/how-abc-lega…
1
3
2
16
3,879
Jess Yan retweeted
So what if Claude wrote files straight onto my disk... And what if every session got a fresh computer... And what if my API key never touched any of it... Well you can. It's Claude Managed Agents on Sprites. docs.sprites.dev/integration…
4
7
4
50
7,304
We continue to release more performance primitives for you to control - still in simple, easy-to-use interfaces.
We've just added several new features to Claude Managed Agents. You can now configure effort levels per agent, seed sessions with events, add up to 500 skills per session, use webhooks for environments + memory stores, and stream events for sub-agents.
2
1
8
1,842
Super excited to ship these -- some of our most common feature requests since we launched 🙌🏻
New from Code with Claude Tokyo: scheduled deployments and environment variables in vaults are in public beta in Claude Managed Agents, and dynamic workflows in Claude Code are generally available. Agents now run on a schedule, use your tools securely, and take on bigger jobs.
16
1,920
here's a few tips for designing self-correction loops and utilizing memory with Fable 5: xitter.cf/RLanceMartin/status/20…
6
64
3
420
99,345
Jess Yan retweeted
Introducing Claude Fable 5: a Mythos-class model that we’ve made safe for general use. Its capabilities exceed those of any model we’ve ever made generally available.
4,905
14,050
9,951
103,160
57,750,770
Jess Yan retweeted
Final stop: Tokyo. Register to hear directly from the teams behind Claude: claude.com/code-with-claude/…
Code with Claude, our developer conference, returns next week. Whether you're just getting started with Claude Code or you've been building for a while, there's a session for you. Register for the livestream: claude.com/code-with-claude
154
522
144
4,869
1,189,380
Love how @Amplitude_HQ was able to put together a design agent in ~2 days with @claudeai and @Cloudflare
Building an agent from scratch teaches you so much about LLMs and the stack *around* the model - I highly recommend it. Cloudflare + Anthropic made it super easy. Wrote up the whole build you can copy: amplitude.com/blog/design-ag…
2
21
5,253
Agentic infrastructure that's modular. You can switch easily between our cloud and yours using the same core primitives.
Live from Code with Claude London: we're launching self-hosted sandboxes (public beta) and MCP tunnels (research preview) in Claude Managed Agents. Run agents inside your own perimeter, with your security controls applied by default.
13
1,003
Jess Yan retweeted
Next stop: London. Register to tune in tomorrow for deep dives, demos, and conversations with the teams behind Claude: claude.com/code-with-claude/…
Code with Claude, our developer conference, returns next week. Whether you're just getting started with Claude Code or you've been building for a while, there's a session for you. Register for the livestream: claude.com/code-with-claude
245
205
29
2,987
542,862
Give your GTM agents access to your codebase. Get them close to the source of truth and translate it; depth not breadth. Your next quarter of ships lives in your PR's and feature flags. Your 6-12 mo roadmap lives in your specs and architecture decisions. It's all code now
1
1
12
847