Claude Managed Agents
AI overview
Sign in and the AI will write an overview from our coverage.
Headlines · 9
- Anthropic Japan BDR runs his day with a fleet of Claude Managed Agents
A business development representative on Anthropic's Japan team describes how he moved repetitive work — routing inbound leads, drafting Japanese and English customer emails, updating Salesforce records and summarizing meetings — onto a fleet of agents called the Nakama, built on the beta Claude Managed Agents infrastructure. According to the post, the agents run on schedules in the background, share one memory store so corrections learned by one agent propagate to the others, and draw credentials from scoped managed vaults, while items needing follow-up are handed to Claude Tag in Slack. He runs rule-based agents on Claude Sonnet and judgment-heavy ones on Claude Opus, and says the setup saves him roughly 60 hours of work per week, a figure based on his own time estimates.
Claude Blog · 🔥 7 - Anthropic frees Claude subscription credits for third-party apps
Anthropic updated an official support page confirming that the monthly API credits of Claude Max and Team subscribers can be used with the Claude Agent SDK, the Claude -p command, the Claude API, Claude Managed Agents, and third-party apps built on those technologies. 36Kr and AIbase both frame this as establishing a BYOS (Bring Your Own Subscription) model, so users pay only once while developers no longer absorb API costs themselves. 36Kr says the support page was updated on October 7 and cites multiple Anthropic employees confirming the policy on Hacker News; claims about an imminent ecosystem boom or a historic loosening are the sources' own commentary.
36氪 人工智能 · 🔥 3 - Claude Platform adds OpenTelemetry agent tracing in public beta
Anthropic announced OpenTelemetry (OTel) traces from Claude Managed Agents, the Messages API and the Claude SDKs on the Claude Platform, now in public beta, sending agent turns, model calls and tool use to any tool that accepts a standard OTLP endpoint. Managed Agents and the Messages API require a destination configured in the Claude Console, while the SDKs export traces automatically; the data follows OpenTelemetry GenAI semantic conventions and works with Grafana Cloud, Honeycomb, Sentry, Splunk, Datadog, Langfuse, LangSmith, New Relic, PostHog, Arize AI and Braintrust, and can also route to Databricks Unity Gateway for per-team token tracking. The post quotes customers saying Ramp used trace-based evaluation to cut token usage 10–20% and make sessions 30% faster on some agents, a vendor-supplied customer claim.
Claude Blog · 🔥 0 - Anthropic adds Dynamic Workflows to Claude Managed Agents
Anthropic launched Dynamic Workflows for Claude Managed Agents in beta on October 9: Claude generates an orchestration program from the task, and a server executes it in the background, spawning sub-agents, passing intermediate results between stages and deciding when to branch or retry, so the main agent does not handle every hand-off. Per Anthropic's documentation, a single run can spawn at most 1,000 agents cumulatively, with 64 concurrent threads and a 24-hour default limit; at an AI Engineer New York 2026 workshop, Anthropic's CJ Avilla and Harrison Stall demoed a stock watchlist scan that split stocks across agents, checked results and produced a report. Anthropic says sub-agents cannot message each other directly and their threads are archived when a run ends, a completed status only means the program finished, and a session budget pauses new requests at the cap while in-flight requests still complete, so costs can exceed it; no built-in self-improvement is included.
InfoQ 中文 AI&大模型 · 🔥 0 - Cisco unveils Webex AI agents for meetings and customer service
At WebexOne on Oct. 7, Cisco announced new agentic capabilities for Webex that let AI agents use shared context to carry out multi-step tasks across collaboration and customer-service systems — for example, @mentioning an analytics agent in a Webex space for usage stats, then asking a presentation agent to update a PowerPoint deck. The announcements include Dialog, a layer meant to maintain customer context across interactions, plus planned features letting agents join Webex spaces, meetings and calls; Cisco says those agents are powered by Claude Managed Agents, while a Webex Suite Model Context Protocol (MCP) integration brings Webex context into OpenAI dots. Several features remain forthcoming: Dialog is expected in beta in the first quarter of calendar 2027, Agent Observability with Splunk is planned for general availability in December 2026, and dots within Webex is slated for a future release.
TechRepublic · 🔥 0 - Anthropic's Claude Managed Agents add dynamic workflows for self-orchestrating agents
At the AI Engineer conference in New York, Anthropic technical staff CJ Avilla and Harrison Stall presented dynamic workflows ("flows"), a feature announced the previous Friday as part of Claude Managed Agents that lets Claude decide and orchestrate its entire multi-agent topology: a lead agent makes a plan, writes an orchestration program, launches subagents and collects results, so developers no longer configure a coordinator and roster by hand. Flows are available in Claude Console; in a stock-watchlist demo they cost "much more" than a single-agent approach but were better at finding all the details, and developers can set a session budget while the model itself does not know its budget at runtime. The speakers also pointed to the "dreaming" research preview for reorganizing memory stores, noted that subagents share a filesystem but cannot message each other through the API, and said flows do not self-improve on their own.
Latent Space · 🔥 0 - Anthropic tests Claude Health for web and mystery 'Iggy'
TestingCatalog reports that Anthropic is testing two previously unseen entries in Claude's navigation under the internal codenames Arborio and Iggy. Arborio carries a heart-in-hand icon and is thought to relate to Claude Health: Anthropic already offers health and fitness data analysis in its iOS and Android apps, where US Pro and Max subscribers can review activity patterns and sleep trends, and Arborio could extend that to a dedicated web dashboard; Iggy shows only a sun icon and its purpose is unknown, with one unconfirmed possibility being a consumer-facing agent that acts proactively. The report stresses that both are internal names that will not ship as such, and that functionality and release timing are unconfirmed; Anthropic already has developer-facing infrastructure in Claude Managed Agents (launched in April) and earlier tested Conway, an always-on agent environment whose internal access ended July 24.
TestingCatalog · 🔥 0 - Anthropic adds dynamic workflows to Claude Managed Agents, up to 1,000 agents
Anthropic announced on October 9 that Claude Managed Agents now supports dynamic workflows, entering public beta: a lead agent writes a plan, distributes subtasks to sub-agents and merges their results, with up to 1,000 agents launched per execution (the documentation lists 64 concurrent threads and notes that limit may change). In an internal test, Anthropic hid 70 bugs in a 116,000-line codebase and said a single agent caught 14 to 27 per run while the dynamic workflow consistently found 66; the company also warns the workflows burn a lot of tokens and recommends starting small. Developers enable it by setting the multiagent type to "multiagent_20261001", or get started with "/claude-api managed-agents-onboard" in Claude Code. A Chinese report says Claude Code Projects also widened its beta to waitlisted Pro and Max users around the same time.
The Decoder · 🔥 0 - Anthropic publishes reference implementation for agent automations
Anthropic's Claude developer blog published a walkthrough of a reference implementation built on Claude Managed Agents (beta) that reads custom sources such as Slack channels and GitHub repos on a schedule, tracks what changed since the last run, and posts a brief to Slack. The post focuses on common failure modes — treating a failed source read as "nothing new," using fixed time windows that create gaps or repeats, and recording a post before it is confirmed — and describes agent.md rules, per-source bookmarks, memory stores, vault credentials, and per-run spending caps to address them. It also provides a /claude-api managed-agents-onboard command to configure the agent interactively in Claude Code.
Claude Developer Blog · 🔥 0
Experience and discussion from the community
Share my Claude Managed Agents experienceAsk about Claude Managed Agents
Nobody has shared their experience with Claude Managed Agents yet.