Claude Fable 5 能够独立承担长期、复杂的工作。以下是如何在 Claude Cowork 中充分利用它，从仅有一个想法开始，直至完成最终成果。
- 分类企业级 AI
- 产品Claude Cowork
- 日期2026 年 7 月 16 日
- 阅读时间5分钟
- https://claude.com/blog/working-with-claude-fable-5-in-claude-cowork
Claude Fable 5 是 Anthropic 目前能力最强的通用模型，专为长时间运行、复杂且异步的工作而构建。Claude Fable 5 尤其擅长独立执行多步骤工作流（例如，进行深度研究并将其整合到初稿备忘录中，在生成董事会演示文稿前进行尽职调查，或遍历文件夹以审查多份合同，仅举几例），并能在此过程中持续测试和评估自身结果。
要最大化该模型的能力，需要改变你与它协作的方式。随着模型不断改进，我们优化了从 Claude 中获得更多价值的建议，包括提示词最佳实践、提供上下文，以及构建用于捕获可重复流程（如每周团队更新、销售电话准备或客户反馈分析）的技能。这些实践对于 Claude Fable 5 仍然重要，事实上，有了这些实践，模型的表现会更好。
Claude Fable 5 能将你的上下文、偏好和技能应用于整个任务，即使是那些需要数天才能完成的任务，而之前的模型可能在长时间跨度中丢失线索，需要反复提醒。与它协作类似于与一位能力出众的同事共事：你说明情况，就最终成果的理想形态达成一致，然后让这位同事去工作。你花在检查每个步骤上的时间更少，因此可以将更多时间用于决定工作应该是什么。
我们为 Claude Fable 5 编写的提示词指南提供了详细的能力改进列表，以及推荐的行为和提示词变更。在本文中，我们将介绍其中一些变更如何应用于 Claude Cowork——Anthropic 面向知识工作的智能体 AI 系统。
Claude Fable 5 如何与 Claude Cowork 互补
Claude Cowork 专为完成成品而设计。给它一个目标，它就能管理其余所有环节，即使任务庞大而复杂。一项大任务会被拆解成多个可同时运行的部分，每个部分都有各自的子智能体——即一个独立的 Claude 实例，负责完成其中一部分任务并汇报结果。这就是 Claude 能够快速处理大量信息的方式。此外，Claude 还通过在一开始制定计划来管理大型任务，并能在执行过程中对照计划检查自身结果。
Claude Fable 5 在处理冗长复杂的任务方面遥遥领先于我们的其他模型，而 Claude Cowork 的任务往往正是如此，包含数十个步骤，每一步都建立在前一步的基础上。以根据今年的实际数据制定明年预算这样的项目为例。Claude 能够访问并读取电子表格，提取运行率，预测每个项目，将预测结果与目标进行核对，并撰写总结。如果它在早期误读了一个运行率，这个错误就会蔓延到后续的每一个预测中。Claude Fable 5 会在开始前规划工作流程，并在执行过程中检查结果，因此它能在任务运行期间发现误读的数字并加以纠正。
决定何时使用 Claude Fable 5
Claude Fable 5 并非 Claude Cowork 中的默认模型；你需要手动选择它。截至本文发布时，默认模型是 Claude Sonnet 5，它适合处理你本人可以快速完成的日常任务。Claude Opus 是处理结构清晰、你明确知道最终结果样子的深度工作的可靠选择。Claude Fable 5 则适用于那些感觉最复杂或最模糊的项目，这些项目可能是之前的模型无法胜任的。它会花费更多时间进行思考，也会消耗更多你的使用额度，但对于那些耗时或出错代价高昂的工作来说，这可能是值得的。我们建议你将 Claude Fable 5 保留给最重要的工作，尤其是那些需要使用多种工具并需要一系列判断决策的任务。
你可以通过 Claude 的努力程度设置进一步调整选择。在较高努力程度下，Claude Fable 5 在启动任务前会进行更多规划，并在执行过程中更频繁地检查进度。对于你期望 Claude 从头到尾完成的复杂或多步骤项目，建议保持较高的努力程度。在较低努力程度下，你仍能利用 Claude Fable 5 的智能，同时获得更快的响应速度。可考虑将其用于那些仍需要前沿判断、但无需深度探索的任务，例如由许多简单步骤组成的智能体运行，或结果易于 Claude 检查的工作。在我们的测试中，较低努力程度下的 Claude Fable 5 通常能达到或超越早期模型在最高努力程度下的表现。如需更深入的技术细节，我们在 Claude Code 中解释了模型选择与努力程度如何相互影响。
同样值得注意的是，Claude Fable 5 配备了一套全新的分类器：这些独立的 AI 系统用于检测与网络安全、生物学或化学相关的请求中可能存在的滥用行为。当它们被触发时，响应将自动由 Claude Opus 4.8 处理，并且用户会在每次发生这种情况时收到通知。Opus 4.8 本身也是一款能力极强的模型，此后对话将保持在 Opus 上；开启新对话即可回到 Claude Fable 5。我们保守地调整了这些安全防护措施，以便能够安全且快速地发布一款 Mythos 级模型供通用使用，因此它们有时会拦截无害的请求，包括 Claude Cowork 中仅涉及相关话题的表述。我们正在努力减少这些误报，同时不断优化安全防护机制。
从一个想法开始，哪怕它微不足道
当你启动一项任务时，你并不总是清楚自己想要达成什么目标。在这个早期的探索阶段，Claude Fable 5 可以成为一个强大的思维伙伴，而在 Claude Cowork 中，它会基于你的技能、工具和知识来开展工作。
例如，当你看到一条与你所在行业或公司相关的新闻公告时，你可以问 Claude：“这是公告内容，结合你对我的组织的了解，告诉我这对我们意味着什么。” 你阅读输出结果，并开始制定策略，与此同时，Claude 会在同一个 Claude Cowork 对话中（也就是头脑风暴发生的地方）制定计划，来生成你所需的素材。
在 Claude Cowork 中进行头脑风暴，能让模型获得你真实的素材进行思考：它可以在你交谈时读取你分享的文件，并使用你连接的工具，从而提供相关的建议。它能在想法还容易修改的阶段就发现其中的漏洞，并向你展示你未曾考虑过的方向。而当任务在同一个对话中开始时，Claude Fable 5 已经承载了你确定的目标、你提出的约束条件，以及你一路走来所做的决策。
例如，Anthropic 的一位数据科学家带着一个关于新分析仪表盘的想法来到 Claude Cowork，当时团队还在琢磨这个仪表盘应该展示什么内容。由于 Claude Fable 5 能在对话过程中读取团队的使用数据，它知道哪些问题需要数周才能被发现，并对那些本可以更早发现这些问题的指标进行了排序。对话结束时，这位数据科学家得到了一份值得添加的指标候选清单和一个可点击的原型。
以下两个提示词可以帮助你将想法演变为输出成果：
- 让 Claude 对你进行访谈：“在开始之前，先问我所有你需要了解的信息，以确保做对这件事。”
- 寻求方向指引：“这是我大致想要的东西。给我三种你可以实现它的方式，每种附带一个快速示例。”
提供包含约束条件的上下文
上下文是 Claude 赖以工作的信息，在 Claude Cowork 中，这意味着你的提示词、你分享的任何文件和文件夹，以及你连接的任何工具，例如 Asana、Hubspot、Jira、Slack 等。
当你在 Claude Cowork 中给 Claude Fable 5 布置任务时，可以想象一下你如何向同事简要说明一份报告。你不会递给他们一列规则，但很可能会告诉他们这份报告是给谁看的、什么时候需要、以及需要达成什么目标，然后相信他们能据此做出正确的决策。Claude Fable 5 的工作方式也是如此。
约束条件仍然有用：“控制在两页以内，使用通俗语言”就是一条不错的指令。但约束条件只告诉 Claude 不能做什么。上下文则告诉它这份工作的目的是什么，这样它就能在你设定的约束条件未能预见的情况下做出正确的判断。
Claude Fable 5 能够很好地处理长篇幅、多步骤的任务，部分原因就在于这种上下文：当它在工作中遇到问题或需要决策时，它会从你提供的上下文中寻找答案。它还会利用这些上下文在过程中自我检查，因此请给它一些具体的参照物，比如一份报告的初稿和最终版本，Claude 就能根据两者之间的变化推断出你的标准是什么。
上下文还能让 Claude 了解你的具体情况，因此它可以推断或找出你在提示词中从未明确说明的细节。分享更多的上下文，能让 Claude 在比你提示词所能容纳的更广泛的知识库中进行搜索。
关于包含大量上下文的对话，有一点需要注意：为了保持信息同步，Claude 会在你每发送一条新消息时重新阅读整个对话，因此长对话可能会消耗你更多的使用量。在新对话中开始新任务会有所帮助。定时任务也会计入你的使用额度，所以请偶尔检查一下，并关闭任何你不再需要的任务。
将更大、更复杂的任务委托给 Claude Fable 5
你可能习惯于将任务分解成多个部分，然后为每个部分分别向 Claude 提供提示词。Claude Fable 5 需要的这类中间提示词要少得多，因此你可以在 Claude Cowork 中直接委托完整的任务。
当流程本身对你很重要时，你仍然应该自己写出步骤，例如某个指标每次都必须以完全相同的方式计算。但如果结果才是关键，那就描述目标，让 Claude 来完成其余工作。分步骤的提示词也可能将其限制在你想到的那些步骤上；而一个目标则能给它留出空间，去寻找更好的路径。
在 Claude Cowork 中进行委托，意味着将你通常自己做的决策交给 Claude。以下是你实现这一点的三种方式：
- 委托方法：将材料交给 Claude，并描述你期望的结果，例如，“这是上个季度的客户反馈。找出取消率上升的原因以及我们应该改变什么。” 浏览那个文件夹可能有几种合理的方法，而正确的方法取决于反馈内容。这正是 Claude Fable 5 擅长的选择：它会阅读所有内容，选择一种方法，并在将结论提交给你之前，对照反馈进行核查。你无需指定它如何得出答案的细节，就能评判这个答案。
- 委托流程：一个技能教会 Claude 你团队使用的流程——如何构建报告、格式化演示文稿、运行分析。你不需要说明要使用哪些技能或按什么顺序使用。只需说“像我们一贯做的那样整理季度回顾”，Claude Fable 5 就会在正确的时机选择正确的技能。
- 委托时机：对于你希望重复进行的工作，描述结果，Claude 就会设定好时间表并将其转化为一个周期性任务：“我想每周一都知道管道中发生了什么变化，以及哪些事情需要做出决策。”
交给 Claude Fable 5 比你所习惯交给 AI 的更困难的工作，甚至是你认为不可能完成的工作。即使工作内容杂乱或不明朗，或者可能需要数小时甚至数天才能完成。描述它，看看模型能否胜任那个级别的工作。挑选一个你负责的结果，说明你将如何评判它，然后让 Claude 提出达成该结果的步骤。其中一些工作可能会变成一个自动运行的定时任务。Claude 可以将该流程保存为一个技能，并设定时间表，通过你已经连接的工具来执行。
审查 Claude 的思考过程
Claude Fable 5 之所以能承载长时间工作，部分原因在于它懂得如何制定并良好地遵循计划。在 Claude Cowork 中，你可以在 Claude 工作时看到这份计划：对话旁的侧边栏列出了它打算执行的操作，随后是它正在读取和写入的文件，以及它正在使用的工具和技能。
这个侧边栏让你有机会及早发现问题并调整方向。那些你原本会在最终输出中发现的错误，现在会以计划中一个错误步骤的形式呈现出来。你可以用一句话修正计划，Claude 会据此调整，无需从头开始。
工作完成后，你可以像审阅同事的成果一样进行复核：打开 Claude 生成的文件并阅读。如果发现任何不妥，运行记录仍保留在对话中。向上滚动浏览 Claude 工作时列出的步骤，包括它读取的文件和使用的工具，并展开它的思考过程，查看某个决策背后的推理依据。或者直接提问：“这个数字从哪来的？”Claude 会为你指出来源。
从你懂得如何验证的工作开始，比如为你的团队起草下一季度的计划初稿。如果你对优先事项非常了解，就能快速判断 Claude 的成果是否站得住脚。当结果证明可靠后，再委派更大的任务。
投入优化你的 Claude Cowork 设置
更强大的模型会提升你已建立的每一项连接的价值，从你共享的文件夹到你的团队使用的工具。以下是我们关于为 Claude Fable 5 提供其发挥最佳性能所需上下文的建议：
- 连接你的工具：首先将 Claude 连接到你的日常工具，例如你的电子邮件、日历、文档或团队聊天。每建立一项连接，都能拓宽 Claude 的能力范围，无需你手动复制粘贴内容。Claude Fable 5 擅长判断何时值得使用某个工具：连接好你的工具后，当答案就在你的日历或聊天记录中时，它会主动去获取，而不是等待你指明方向。
- 将写作风格调整至符合你的表达习惯：每一款新模型都有其默认的写作风格，包括语气、篇幅以及输出时优先使用的措辞。你可能会注意到 Claude Fable 5 存在某些默认倾向，例如在较长的对话中，写作风格会变得更为简洁或难以跟上。语气、语调和风格都可以轻松定制；你可以通过提示词或将其添加到项目指令中，根据个人偏好进行调整。例如，你可以添加类似“使用平实、直接、简洁的语言”这样的指令。如果你使用了记忆功能，请偶尔检查一下 Claude 保存了哪些关于你写作偏好的信息。对于需要特定风格的文档，可以使用连接器或现有文件，让 Claude 阅读你过去的写作内容，并将其发现保存为一项技能，以便在下次进行类似工作时调用。我们发现，Claude Fable 5 比早期模型更严格地遵循既定指令，并且在需要时能更好地利用已保存的资料。
- 重新审视你为早期模型所做的设置：为早期模型保存的指令（如技能和记忆文件）通常包含该模型所需的修正。如果直接沿用，这些旧的修正可能会限制新模型的表现。请让 Claude Fable 5 进行一次审查：“检查我的技能和已保存的记忆。哪些仍然适用，哪些是为旧模型编写的？”
未来展望
随着前沿智能的持续发展，Claude Cowork 将变得越来越强大，能够支持更长时间的工作，并解锁更多知识工作应用场景。学习如何编写提示词、管理上下文、检查 Claude 的工作成果以及委派任务，将帮助你充分利用 Claude Fable 5 及未来模型的所有功能。
本文由 Anthropic 教育团队的 Josefina Albert 撰写。
立即开始使用 Claude Cowork。
Claude Fable 5 can carry long, complex work on its own. Here’s how to get the most out of it in Claude Cowork, starting with as little as an idea and getting to finished work.
- Category
- ProductClaude Cowork
- DateJuly 16, 2026
- Reading time5min
- https://claude.com/blog/working-with-claude-fable-5-in-claude-cowork
Claude Fable 5 is Anthropic’s most capable generally available model, built for long-running, complex and asynchronous work. Claude Fable 5 is particularly effective carrying out multi-step workflows (such as conducting deep research that it incorporates in a first-draft memo, performing due diligence before generating board presentations, or going through a folder to redline multiple contracts, to name a few) on its own for extended periods of time, testing and evaluating its results as it goes.
Maximizing the model’s capabilities requires a change in how you work with it. As models improve over time, we've refined our recommendations for getting more out of Claude, including prompting best practices, providing context, and building skills that capture repeatable processes like weekly team updates, sales call prep, or customer feedback analysis. Those practices still matter with Claude Fable 5, in fact, the model performs even better with them in place.
Claude Fable 5 applies your context, preferences, and skills across entire tasks, even those that take days to complete, while previous models may have lost track over long stretches and needed reminding. Working with it resembles working with a highly capable colleague: you explain the situation, agree on what a strong final result looks like, and let your colleague work. Less of your time goes to checking each step, so more of it can go to deciding what the work should be.
Our prompting guide for Claude Fable 5 provides a detailed list of capability improvements and recommended behavior and prompting changes. In this article, we cover how some of those apply to Claude Cowork, Anthropic’s agentic AI system for knowledge work.
How Claude Fable 5 complements Claude Cowork
Claude Cowork is built for creating finished work. Give it an objective, and it manages the rest, even when the task is large and complex. A big job gets broken into parts that run at the same time, each with its own subagent, a separate instance of Claude that takes one part of the job to complete and reports back. That is how Claude gets through large amounts of information quickly. Claude also manages large tasks by setting a plan at the start, and it can check its own results against it as it goes.
Claude Fable 5 has a wide lead over our other models on long, complex tasks and Claude Cowork tasks are often exactly that, with dozens of steps, each building on the last. Take a project like building next year’s budget based on this year’s actuals. Claude gets access to and reads the spreadsheets, pulls the run rates, projects each line, reconciles the projections against targets, and writes the summary. If it misreads a run rate early, the error will flow into each projection after it. Claude Fable 5 plans the workflow before starting and checks results as it goes, so it can catch the misread number while the job runs and correct it.
Decide when to use Claude Fable 5
Claude Fable 5 isn’t the default model in Claude Cowork; you need to select it. As of the time of publication, the default is Claude Sonnet 5, and it is the right choice for everyday tasks you yourself would handle in quick passes. Claude Opus is a dependable choice for deep work with a clear shape, where you know what the end result looks like. Claude Fable 5 is for the projects that feel the most complex or ambiguous, and may have been out of reach for prior models. It spends more time thinking and more of your usage limits, but that may be worth it on work that’s time-consuming or costly to get wrong. We recommend that you reserve Claude Fable 5 for your most important work, especially jobs that use multiple tools and require a series of judgment calls.
You can further tune your choice with Claude’s effort setting. At higher effort, Claude Fable 5 plans more before it kicks off a job and checks in more throughout its run. Keep effort higher for complex or multi-step projects you expect Claude to complete from beginning to end. At lower effort, you’ll get a faster response, while still taking advantage of Claude Fable 5 intelligence. Consider using it for tasks that still need frontier judgement, but not deep explorations, such as agentic runs made of many easy steps or work where the result is easy for Claude to check. In our testing, Claude Fable 5 at lower effort often matched or exceeded the performance of earlier models at their highest effort levels. For a more detailed look under the hood, we explain how model choice and effort interact in Claude Code.
It’s also worth noting that Claude Fable 5 comes with a new set of classifiers: separate AI systems that detect potential misuse in requests related to cybersecurity or to biology and chemistry. When they trigger, the response is automatically handled by Claude Opus 4.8 instead, and users are informed whenever this occurs. Opus 4.8 is a highly capable model in its own right, and the chat stays on Opus from there; start a new one to get back to Claude Fable 5. We tuned these safeguards conservatively so we could release a Mythos-class model for general use both safely and quickly, so they'll sometimes catch harmless requests, including phrases in Claude Cowork that only touch on related topics. We're working to reduce these false positives as we refine the safeguards.
Start with as little as an idea
When you kick off a task, you don't always know what you're trying to accomplish. That early stretch is where Claude Fable 5 can be a powerful thought partner, and in Claude Cowork it works from your skills, tools, and knowledge.
For example, if you see a news announcement relevant to your industry or company, you can ask Claude: "Here's the announcement, tell me what changes for us, considering everything you know about my organization." You read the output and as you start to develop a strategy, Claude builds a plan to produce the assets that you need, starting in the same conversation in Claude Cowork where the brainstorming happened.
Brainstorming in Claude Cowork gives the model your real material to think with: it can read the files you've shared and use the tools you've connected while you talk, so it can offer relevant suggestions. It notices gaps in an idea while the idea is still easy to change, and it shows you directions you hadn't considered. And when the task begins in the same conversation, Claude Fable 5 already carries the goal you settled on, the constraints you named, and the decisions you made along the way.
For example, a data scientist at Anthropic came to Claude Cowork with an idea for a new analytics dashboard while the team was still figuring out what it should show. Because Claude Fable 5 could read the team's usage data during the conversation, it knew which problems take weeks to get noticed, and it ranked the metrics that would have caught them sooner. By the end of the conversation, the data scientist had a shortlist of metrics worth adding and a clickable prototype.
Here are two prompts that can help you evolve your idea into an output:
- Ask Claude to interview you: “Before you start, ask me everything you need to know to get this right.”
- Ask for directions: “Here is roughly what I want. Give me three ways you could take it, with a quick sample of each.”
Provide context with your constraints
Context is the information Claude works from, and in Claude Cowork that means your prompt, whatever files and folders you’ve shared, and any tools you’ve connected, such as Asana, Hubspot, Jira, Slack, or others.
When you give Claude Fable 5 a task in Claude Cowork, think of how you'd brief a colleague on a report. You wouldn't hand them a list of rules, but chances are you'd tell them who it's for, when it's needed, and what it has to accomplish, and trust them to make good decisions from there. Claude Fable 5 works the same way.
Constraints are still useful: "keep it under two pages and use plain language" is a fine instruction. But a constraint only tells Claude what not to do. Context tells it what the work is for, so it can make the right call in situations your constraints didn't anticipate.
Claude Fable 5 handles long, multi-step tasks well partly because of this context: when a question or decision point comes up while it works, it looks for the answer in the context you shared. It also uses that context to check its own work as it goes, so give it something concrete to judge against, such as an early draft of a report and the final version, and Claude will work out what your standards are based on what changed between the two.
Context also gives Claude an understanding of your situation, so it can infer or find details you never specified in the prompt. Sharing additional context lets Claude search through a wider base of knowledge than you could fit in a prompt.
One thing to note about chats with lots of context: in order to stay caught up, Claude reads the whole conversation again with every new message you send, so a long conversation may use more of your usage. It helps to start new tasks in a fresh conversation. Scheduled tasks count towards your limit too, so check yours occasionally and turn off any you no longer need.
Delegate larger, more complex jobs to Claude Fable 5
You may be used to breaking a task into parts and prompting Claude for each one. Claude Fable 5 needs far fewer of those intermediate prompts, so you can delegate complete jobs in Claude Cowork.
You should still write out the steps yourself when the process matters to you, for example if a metric has to be calculated the exact same way each time. But if the outcome is what matters, describe the goal and let Claude do the rest. A step-by-step prompt can also limit it to the steps you thought of; a goal gives it room to find a better path.
Delegating in Claude Cowork means handing Claude a decision you would normally make yourself. Here are three ways you can do that:
- Delegate the approach: Give Claude the material and describe the outcome you want, for example, "Here is last quarter's customer feedback. Find out why cancellations rose and what we should change." There may be several reasonable ways through that folder, and the right one depends on what's in the feedback. That's a choice Claude Fable 5 makes well: it reads everything, picks an approach, and checks its conclusion against the feedback before bringing it to you. You can judge the answer without needing to specify the details of how it gets there.
- Delegate the procedure: A skill teaches Claude a procedure your team uses—how you build a report, format a deck, run an analysis. You don't need to say which skills to use or in what order. Say "put together the quarterly review the way we always do it," and Claude Fable 5 picks the right skills at the right moment.
- Delegate the timing:For work you want repeated, describe the outcome and Claude will set up the schedule and turn it into a recurring task: "I want to start every Monday knowing what changed in the pipeline and what needs a decision."
Bring Claude Fable 5 harder work than you're used to giving AI, even work you assumed wasn't possible. Even if the work is messy or unclear, or could take hours or days to finish. Describe it and see whether the model can work at that level. Pick an outcome you're responsible for and say how you'd judge it, then let Claude propose the steps to get there. Some of this work may turn into a scheduled task that runs on its own. Claude can save the procedure as a skill and put it on a schedule, working through the tools you're already connected to.
Review Claude’s thought process
Part of what lets Claude Fable 5 carry long work is that it knows how to set and follow a plan well. In Claude Cowork, you can see that plan while Claude works: the panel beside the conversation lists what it intends to do, then the files it's reading and writing and the tools and skills it's using.
That panel is your chance to catch problems and redirect early. A mistake you'd otherwise find in the finished output instead shows up as one wrong step in the plan. You can correct the plan in one sentence and Claude adjusts without starting over.
When the work is finished, review it the way you would a colleague's: open the files Claude produced and read them. If something appears off, the record of the run is still in the conversation. Scroll back through the steps Claude listed as it worked, including the files it read and the tools it used, and expand its thinking to see the reasoning behind a decision. Or ask directly: "Where did this figure come from?" and Claude will point you to the source.
Start with work you know how to verify, like the first draft of next quarter’s plan for your team. If you know the priorities well, you can quickly tell if Claude’s pass holds up. Delegate bigger jobs as the results prove reliable.
Invest in your Claude Cowork setup
A more capable model raises the value of each connection you’ve made, from the folders you’ve shared to the tools your team works in. Here are our recommendations for giving Claude Fable 5 the context it needs to do its best work:
- Connect your tools:Connect Claude to the tools you use daily first, like your email, calendar, documents, or your team's chat. Each connection widens what Claude can do without you copying things in. Claude Fable 5 is good at deciding when a tool is worth using: with your tools connected, it notices when the answer is in your calendar or a chat thread and goes to get it, instead of waiting to be pointed there.
- Tune the writing to your voice: Each new model arrives with its own writing defaults: voice, length, and phrases it reaches for first in its outputs. You may notice Claude Fable 5 has certain defaults, such as more terse or hard to follow writing style in longer sessions. Voice, tone, and style can easily be customized; you can tailor them to your preferences by prompting or adding them to your project instructions. For example, you can add something like "use plain, straightforward, direct language." If you use memory, check occasionally what Claude has saved about your writing preferences. For documents where you want a specific voice, use connectors or existing files to have Claude read through your past writing and save what it finds as a skill it can call on the next time you do similar work. We've found Claude Fable 5 follows standing instructions more closely than earlier models, and is better at using saved material when needed.
- Revisit what you set up for earlier models:Saved instructions, like Skills and memory files, written for an earlier model often carry corrections that model needed. Carried forward, old corrections can constrain a new model. Ask Claude Fable 5 to do an audit: 'Go through my skills and saved memory. Which still fit, and which were written for an older model?'
What comes next
As frontier intelligence continues to evolve, Claude Cowork will become increasingly capable, enabling even longer running work and unlocking additional knowledge work use cases. Learning how to prompt, manage context, check Claude’s work, and delegate tasks will help you take advantage of all Claude Fable 5 and future models have to offer.
This article was written by Josefina Albert on Anthropic’s Education team.
Get started with Claude Cowork today.