Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

We’ve added a few updates to Claude Managed Agents: Streaming session event deltas, per-session agent overrides, new webhook event types, reverse pagination, and credential injection scoping.

ClaudeDevs's profile picture

ClaudeDevs

667,060 subscribers

343,458 görüntüleme • 2 ay önce •via X (Twitter)

Bilim & Teknoloji
LIVE

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

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.
0:24

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.

ClaudeDevs

590,136 görüntüleme • 1 ay önce

Finally, we've redesigned the Console session viewer for multi-agent sessions. It now has a minimap with one lane per agent, a streaming transcript grouped by agent iteration, and an inspector with cost in dollars per thread and per session. Live now:
0:36

Finally, we've redesigned the Console session viewer for multi-agent sessions. It now has a minimap with one lane per agent, a streaming transcript grouped by agent iteration, and an inspector with cost in dollars per thread and per session. Live now:

ClaudeDevs

54,506 görüntüleme • 16 gün önce

We've added a new cookbook: connect a Claude Managed Agent to Vercel's Chat SDK. This gives an agent access to a universal chat layer.
0:30

We've added a new cookbook: connect a Claude Managed Agent to Vercel's Chat SDK. This gives an agent access to a universal chat layer.

ClaudeDevs

393,353 görüntüleme • 8 gün önce

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.
0:21

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.

ClaudeDevs

329,070 görüntüleme • 15 gün önce

Another pattern is agent-to-agent communication, allowing Claude to coordinate and delegate tasks. Claude Managed Agents supports this with multi-agent: agents can use different models, prompts, and tools while sharing sandboxes or vault credentials.
0:38

Another pattern is agent-to-agent communication, allowing Claude to coordinate and delegate tasks. Claude Managed Agents supports this with multi-agent: agents can use different models, prompts, and tools while sharing sandboxes or vault credentials.

ClaudeDevs

68,061 görüntüleme • 1 ay önce

We shipped four updates to Claude Managed Agents this week. First, you can now set a budget for sessions to keep spend predictable. Sessions that hit the limit pause with a budget_reached event, you can raise the budget to resume.
0:36

We shipped four updates to Claude Managed Agents this week. First, you can now set a budget for sessions to keep spend predictable. Sessions that hit the limit pause with a budget_reached event, you can raise the budget to resume.

ClaudeDevs

611,447 görüntüleme • 28 gün önce

In Claude Managed Agents, we’ve added multiagent orchestration, an outcomes loop for rubric-driven self-improvement, dreaming for self-learning, & webhooks.
0:29

In Claude Managed Agents, we’ve added multiagent orchestration, an outcomes loop for rubric-driven self-improvement, dreaming for self-learning, & webhooks.

ClaudeDevs

573,971 görüntüleme • 4 ay önce

We’ve added a CLI for Claude Platform to make every API endpoint runnable from your terminal. Call the Messages API, stand up Claude Managed Agents, pipe results straight into your shell. The ant CLI is well understood by coding agents (Claude Code) using the claude-api skill.
0:30

We’ve added a CLI for Claude Platform to make every API endpoint runnable from your terminal. Call the Messages API, stand up Claude Managed Agents, pipe results straight into your shell. The ant CLI is well understood by coding agents (Claude Code) using the claude-api skill.

ClaudeDevs

1,211,256 görüntüleme • 3 ay önce

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:
0:55

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:

ClaudeDevs

299,927 görüntüleme • 1 gün önce

How do teams get agents into production? New blog post from our Applied AI team on Claude Managed Agents and the challenges it solves (credentials, sandboxing, observability, & more) ...
0:22

How do teams get agents into production? New blog post from our Applied AI team on Claude Managed Agents and the challenges it solves (credentials, sandboxing, observability, & more) ...

ClaudeDevs

427,683 görüntüleme • 2 ay önce

Claude Managed Agents can operate in a sandbox you control, on your own infrastructure or with any provider you choose. Today we added new guides for Blaxel, E2B, Google Cloud, Namespace, and Superserve, so you can choose the best fit for your use case.
0:24

Claude Managed Agents can operate in a sandbox you control, on your own infrastructure or with any provider you choose. Today we added new guides for Blaxel, E2B, Google Cloud, Namespace, and Superserve, so you can choose the best fit for your use case.

ClaudeDevs

515,034 görüntüleme • 2 ay önce

Computer use, the browser tool, the Skills API, and the Files API are now generally available on the Claude Platform. Automate work in applications that have no API with fewer round trips per task, and build Claude Managed Agents on versioned skills and reusable files.
0:59

Computer use, the browser tool, the Skills API, and the Files API are now generally available on the Claude Platform. Automate work in applications that have no API with fewer round trips per task, and build Claude Managed Agents on versioned skills and reusable files.

ClaudeDevs

1,754,332 görüntüleme • 15 gün önce

Claude Tag is the next evolution of agents. It's a proactive, multiplayer agent with memory and identity, built on top of Claude Code. Learn more about how Claude Tag works and best practices for using it in this deep dive.
6:33

Claude Tag is the next evolution of agents. It's a proactive, multiplayer agent with memory and identity, built on top of Claude Code. Learn more about how Claude Tag works and best practices for using it in this deep dive.

ClaudeDevs

452,413 görüntüleme • 2 ay önce

Over the past 6 months, Claude Platform has added new APIs to help developers quickly build and deploy agents. Platform leads Katelyn Lesse, Angela Jiang, and Jess Yan sat down to talk about what has shipped and the patterns we're seeing in production.
0:36

Over the past 6 months, Claude Platform has added new APIs to help developers quickly build and deploy agents. Platform leads Katelyn Lesse, Angela Jiang, and Jess Yan sat down to talk about what has shipped and the patterns we're seeing in production.

ClaudeDevs

268,814 görüntüleme • 1 ay önce

Anthropic has introduced Claude Managed Agents which is a new system designed to help developers build and deploy agents at scale. It combines an agent harness with production infrastructure to move from prototype to launch in days.
0:57

Anthropic has introduced Claude Managed Agents which is a new system designed to help developers build and deploy agents at scale. It combines an agent harness with production infrastructure to move from prototype to launch in days.

Shay Boloor

33,184 görüntüleme • 4 ay önce

IDC South Africa We’ve been through quite a lot. Here’s a few things I’d like to share. When I managed to gatecrash the IDC South Africa hosted event addressing Cyril Ramaphosa 🇿🇦 and 400 academics.
1:25

IDC South Africa We’ve been through quite a lot. Here’s a few things I’d like to share. When I managed to gatecrash the IDC South Africa hosted event addressing Cyril Ramaphosa 🇿🇦 and 400 academics.

🖍

32,591 görüntüleme • 5 ay önce

Introduction to the new Sandbox Agent SDK 🛜 Control coding agents w/ HTTP or TypeScript 🌐 Universal session schema to build UIs easily 🖥️ Any sandbox or Linux/macOS machine 🤖 Claude Code, Codex, OpenCode, and Amp GitHub, docs, and skills below
3:08

Introduction to the new Sandbox Agent SDK 🛜 Control coding agents w/ HTTP or TypeScript 🌐 Universal session schema to build UIs easily 🖥️ Any sandbox or Linux/macOS machine 🤖 Claude Code, Codex, OpenCode, and Amp GitHub, docs, and skills below

Nathan Flurry 🔩

27,651 görüntüleme • 7 ay önce

We're open-sourcing Claude Commerce Agents. This is a blueprint for building shopping and merchant agents, with reference implementations across retail, travel, telecom, and entertainment.
0:30

We're open-sourcing Claude Commerce Agents. This is a blueprint for building shopping and merchant agents, with reference implementations across retail, travel, telecom, and entertainment.

ClaudeDevs

1,966,195 görüntüleme • 2 gün önce

Free LGBTQIA+ Community Event this Saturday. All levels session combining Pilates & Yoga to get you moving better! A low impact session to get you in touch with your body and make some new queer connections Booking link: #LGBTQ #Queer #Manchester
0:57

Free LGBTQIA+ Community Event this Saturday. All levels session combining Pilates & Yoga to get you moving better! A low impact session to get you in touch with your body and make some new queer connections Booking link: #LGBTQ #Queer #Manchester

Evan Garrett

10,587 görüntüleme • 5 ay önce

Today we are announcing Box Agent Security and Governance. AI agents are reading files, moving content, and triggering actions across your most sensitive data at machine speed. Most security tools were not designed for this. Box closes the gap at the content layer: · Prompt injection detection before it reaches the model · Agent guardrails on what agents can and cannot do · Classification-based access policies extending Box Shield to AI · Audit trails for every agent session No additional software. No per-vendor configuration.
0:49

Today we are announcing Box Agent Security and Governance. AI agents are reading files, moving content, and triggering actions across your most sensitive data at machine speed. Most security tools were not designed for this. Box closes the gap at the content layer: · Prompt injection detection before it reaches the model · Agent guardrails on what agents can and cannot do · Classification-based access policies extending Box Shield to AI · Audit trails for every agent session No additional software. No per-vendor configuration.

Box

749,502 görüntüleme • 1 ay önce