今天，我们以研究预览的形式在 Claude Managed Agents 中推出 dreaming。Dreaming 通过回顾过往会话以发现模式、帮助智能体自我改进，从而扩展了 记忆能力。我们还向使用 Managed Agents 构建应用的开发者开放了 outcomes、多智能体编排和 webhooks。这些更新共同让智能体在只需极少引导的情况下，也能更从容地处理复杂任务。
用 dreaming 构建可自我改进的智能体
Dreaming 是 Claude Managed Agents 中的一项定时流程，它会审查智能体会话和记忆存储，提取模式并整理记忆，让智能体随时间不断改进。你可以自行决定想要多少控制权：dreaming 可以自动更新记忆，也可以由你在变更生效前先行审核。
Dreaming 能揭示单个智能体自身无法看到的模式，包括反复出现的错误、智能体逐渐趋同的工作流，以及团队内共享的偏好。它还会重构记忆，使其在演进过程中始终保持高信噪比。这对于长时间运行的工作和多智能体编排尤为有用。
记忆与 dreaming 共同构成了一个强大的记忆系统，服务于可自我改进的智能体。记忆让每个智能体能够在工作过程中捕捉所学到的内容。Dreaming 则在会话之间精炼这些记忆，汇集跨智能体的共享经验并保持其最新状态。
Dreaming 已在 Claude Platform 的 Managed Agents 中提供；开发者可在此申请访问权限。
Outcomes：为智能体工作定义质量标准
借助 outcomes，你编写一份描述成功标准的评分细则，智能体便朝着这个目标努力。一个独立的评分器会在自己的上下文窗口中根据你的标准评估输出，因此不会受到智能体推理过程的影响。当某处不正确时，评分器会指出需要修改的地方，智能体则再进行一轮尝试。
当智能体知道"好"的标准是什么时，它们能发挥出最佳水平。例如，一个结构框架、一项演示标准，或一组需要满足的要求。借助 outcomes，智能体可以对照这一标准检查自己的工作并自我纠正，直到输出足够好，无需人工审查每一次尝试。
Outcomes 对于需要注重细节和全面覆盖的任务尤为有用。它也适用于主观质量，比如文案是否符合品牌调性，或设计是否遵循视觉规范。在测试中，outcomes 相比标准提示词循环将任务成功率提升了最多 10 个百分点，在最难的问题上提升幅度最大。Outcomes 还提升了文件生成质量，在我们的内部基准测试中，docx 的任务成功率提升了 +8.4%，pptx 提升了 +10.1%。
你现在还可以定义一个 outcome，让智能体运行，并在完成时通过webhook收到通知。
多智能体编排：用多个智能体处理复杂任务
当单个智能体难以出色完成的工作量过大时，多智能体编排让一个主导智能体把任务拆解成若干部分，并将每一部分委派给拥有各自模型、提示词和工具的专家智能体。例如，一个主导智能体可以负责开展调查，同时让子智能体分头梳理部署历史、错误日志、指标和支持工单。
这些专家智能体在共享文件系统上并行工作，并共同汇入主导智能体的整体上下文。主导智能体可以在工作流进行中随时与其他智能体再次沟通，因为事件是持久化的，每个智能体都记得自己做过什么。你还可以在 Claude Console 中追踪每一步：哪个智能体做了什么、以什么顺序、以及为什么，让你对任务的委派和执行过程拥有完全的可见性。
各团队正在构建什么
各团队正在利用 dreaming、outcomes 和多智能体编排，交付能够自我验证工作、跨会话学习并并行处理复杂任务的智能体：
- Harvey 使用 Managed Agents 来协调复杂的法律工作，例如长篇起草和文档创建。借助 dreaming，他们的智能体能够记住会话之间学到的东西，包括文件类型的变通方法和特定工具的使用模式。在他们的测试中，完成率提升了约 6 倍。
- Netflix 的平台团队构建了一个分析智能体，用于处理来自不同来源的数百次构建的日志。面对影响数千个应用的变更，关键在于找出在众多应用中反复出现的问题。多智能体编排让该智能体能够并行分析批次数据，并只呈现出值得采取行动的模式。
- Spiral by Every 正在使用多智能体编排和成果（outcomes）来驱动其全新 API 和 CLI 背后的写作智能体。主智能体运行在 Haiku 上：它负责接收传入的请求，在需要时提出简短的追问，然后将起草工作委派给运行在 Opus 上的子智能体。当用户要求生成多份草稿时，子智能体会并行运行。写作质量是 Spiral 的核心价值，因此他们使用成果（outcomes）来保障这一点。每份草稿都会依据一套评分标准进行打分，该标准涵盖 Every 的编辑原则和用户的语气风格，二者均从记忆中调取。只有达到标准的草稿才会被返回。
- Wisedocs 在 Managed Agents 上构建了一个文档质量检查智能体，利用成果（outcomes）依据其内部准则对每次审查进行评分。如今审查速度提升了 50%，同时始终与其团队的标准保持一致。
快速上手
Dreaming 已在研究预览版中提供，outcomes、多智能体编排和记忆功能已作为 Managed Agents 的一部分进入公开测试版。要开始使用 dreaming，请在此申请访问权限。查阅我们的文档以了解更多信息，或访问Claude Console来部署你的第一个智能体。
Today we're launching dreaming in Claude Managed Agents as a research preview. Dreaming extends memory by reviewing past sessions to find patterns and help agents self-improve. We're also making outcomes, multiagent orchestration, and webhooks available to developers building with Managed Agents. Together, these updates make agents more capable at handling complex tasks with minimal steering.
Build self-improving agents with dreaming
Dreaming is a scheduled process in Claude Managed Agents that reviews agent sessions and memory stores, extracts patterns, and curates memories so agents improve over time. You decide how much control you want: dreaming can update memory automatically, or you can review changes before they land.
Dreaming surfaces patterns that a single agent can’t see on its own, including recurring mistakes, workflows that agents converge on, and preferences shared across a team. It also restructures memory so it stays high-signal as it evolves. This is especially useful for long-running work and multiagent orchestration.
Together, memory and dreaming form a robust memory system for self-improving agents. Memory lets each agent capture what it learns as it works. Dreaming refines that memory between sessions, pulling shared learnings across agents and keeping it up-to-date.
Dreaming is available in Managed Agents on the Claude Platform; developers can request access here.
Outcomes: define the quality bar for agent work
With outcomes, you write a rubric describing what success looks like and the agent works toward it. A separate grader evaluates the output against your criteria in its own context window, so it isn't influenced by the agent's reasoning. When something isn't right, the grader pinpoints what needs to change and the agent takes another pass.
Agents do their best work when they know what "good" looks like. For example, a structural framework, a presentation standard, or a set of requirements that need to be met. With outcomes, agents can check their work against that bar and self-correct until the output is good enough, without a human needing to review each attempt.
Outcomes is particularly useful for tasks that require attention to detail and exhaustive coverage. It also works for subjective quality, like whether copy matches a brand voice or a design follows visual guidelines. In testing, outcomes improved task success by up to 10 points over a standard prompting loop, with the largest gains on the hardest problems. Outcomes also improved file generation quality, with +8.4% task success on docx and +10.1% on pptx in our internal benchmarks.
You can also now define an outcome, let the agent run, and get notified by a webhook when it's done.
Multiagent orchestration: Handle complex tasks with multiple agents
When there is too much work for a single agent to do well, multiagent orchestration lets a lead agent break the job into pieces and delegate each one to a specialist with its own model, prompt, and tools. For example, a lead agent can run an investigation while subagents fan out through deploy history, error logs, metrics, and support tickets.
These specialists work in parallel on a shared filesystem and contribute to the lead agent's overall context. The lead agent can check back in with other agents mid-workflow because events are persistent and every agent remembers what it's done. You can also trace every step in the Claude Console: which agent did what, in what order, and why, giving you full visibility into how your task was delegated and executed.
What teams are building
Teams are using dreaming, outcomes, and multiagent orchestration to ship agents that verify their own work, learn across sessions, and parallelize complex jobs:
- Harvey uses Managed Agents to coordinate complex legal work like long-form drafting and document creation. With dreaming, their agents remember what they learned between sessions, including filetype workarounds and tool-specific patterns. Completion rates went up ~6x in their tests.
- Netflix's platform team built an analysis agent that processes logs from hundreds of builds across different sources. With changes that affect thousands of applications, what matters is finding the issues that recur across many of them. Multiagent orchestration lets the agent analyze batches in parallel and surface only the patterns worth acting on.
- Spiral by Every is using multiagent orchestration and outcomes to power the writing agent behind their new API and CLI. The lead agent runs on Haiku: it fields incoming requests, poses quick follow-up questions when needed, then delegates the drafting to subagents running on Opus. When a user asks for multiple drafts, the subagents run in parallel. Writing quality is Spiral's core value, so they use outcomes to enforce it. Each draft is scored against a rubric of Every's editorial principles and the user's voice, both pulled from memory. Only drafts that clear the bar are returned.
- Wisedocs built a document quality check agent on Managed Agents, using outcomes to grade each review against their internal guidelines. Reviews now run 50% faster, while staying aligned with their team's standards.
Getting started
Dreaming is available in research preview, outcomes, multiagent orchestration, and memory are available in public beta as part of Managed Agents. To get started with dreaming, request access here. Explore our documentation to learn more or visit the Claude Console to deploy your first agent.