LectureRechercheRadarCadre d'investissement
Connexion / Inscription
← Retour à la lecture
ActualitésSujet · Claude动态工作流Matériel2 min de lectureRédaction DisconfirmAI

Anthropic Engineers Explain Claude's Dynamic Workflows at AI Engineer Conference: Letting the Model Orchestrate Multi-Agents

This resource recommendation covers a session from the AI Engineer New York 2026 conference. Anthropic Members of Technical Staff CJ Avilla and Harrison Stall introduced the new 'dynamic workflows' feature, demonstrating how Claude autonomously determines agent topology for complex tasks and discussing engineering boundaries regarding token budgets and sub-agent communication.

2026-10-13 02:18 GMT+8

At the AI Engineer New York conference that kicked off on October 12, 2026, Anthropic held a workshop on orchestrating its Claude Managed Agents. According to reporting by tech media outlet Latent Space, CJ Avilla and Harrison Stall, both Members of Technical Staff at Anthropic, focused on introducing a new feature called 'dynamic workflows' (or simply 'flows'). This capability aims to solve the bottleneck developers face when managing large numbers of parallel agents, allowing Claude to write scripts itself to coordinate dozens or even hundreds of sub-agents.

The presenters drew lessons from the evolution of Unix and Linux operating systems, noting that as the number of agents grows, the system requires higher levels of organization. In traditional Claude Managed Agents, developers had to manually configure a coordinator and a roster of sub-agents; in dynamic workflows, the lead agent creates a plan, and Claude generates an orchestration program that launches agents, collects results, and manages information flow. Stall stated that this allows users to accomplish discrete, verifiable units of work without having to manage any of the interconnections between them, enabling the handling of projects far larger than a single conversation context.

Beyond the core mechanism, the live Q&A touched on several key engineering challenges in multi-agent systems. When asked how to prevent simple tasks from triggering too many sub-agents and causing cost overruns, Stall replied that it relies primarily on evaluations ('evals') and lower defaults. Regarding token budgets, he revealed that the model does not know its budget while running, but developers can set a session budget. He humorously added that informing models of their budgets could make the agents 'a little bit anxious.' Additionally, Avilla mentioned a research preview feature called 'dreaming,' which helps repeated workflows become more efficient over time by reorganizing memory stores.

Connexion / Inscription
LectureRechercheRadarCadre d'investissement

Although dynamic workflows cost significantly more than single-agent approaches in demo cases like stock watchlist scanning, Avilla emphasized they are 'much more effective at finding all of the details.' For AI engineers looking to understand how to apply large language models to large-scale code audits, migrations, or cross-checked research, this episode offers up-to-date practical perspectives and design trade-offs directly from a leading vendor.

Sources

  • latent.space↗
  • code.claude.comClaude Code Docs↗
Sujet

Claude动态工作流

Anthropic推出的“动态工作流”(Dynamic Workflows)是Claude Code的一项核心功能,旨在解决复杂任务中多智能体协调的瓶颈。与传统由主Agent逐轮决策不同,该机制让Claude自主编写JavaScript编排…

4 étapes1 piècesMis à jour 2026-10-24 20:49

Comment on en est arrivé là

  1. 2026-05-28Anthropic正式发布Claude Code中的动态工作流功能,宣布其在Pro、Max、Team及Enterprise计划以及API、Amazon Bedrock等平台全面可用。claude.com ↗
  2. 2026-06-02第三方教程指出,动态工作流可自动生成JavaScript脚本,并行启动多达1000个子Agent,用于处理跨文件迁移和深度研究等任务。gaodalie.substack.com ↗
  3. 2026-10-09Anthropic为Claude Managed Agents上线动态工作流的Beta版本,允许服务器在后台执行编排程序,释放主会话线程以处理其他交互。infoq.cn ↗

Ce qui reste non résolu

  • 动态工作流如何更有效地控制Token消耗?目前模型运行时不知晓预算,仅靠会话级硬性上限可能导致超支或中断。
  • 子Agent之间的通信是否仅限于编排程序传递和共享文件系统?未来是否会支持Agent间的直接消息交互以实现更灵活的协作?
  • “Dreaming”功能何时能正式集成到动态工作流中,以实现基于历史经验的自动化流程优化?
Lire le sujet complet →
Continuer la recherche →