指南建议以结果而非步骤开头，用一两条硬性规则替代逐步骤脚本。 Chat 处理快速任务，基于 Codex 技术和 GPT-5.6 模型的 ChatGPT Work 负责多源、多步骤的复杂项目。 Codex 新增 Steer（重定向当前运行）、Queue（排队下一条消息）和沙盒模式，支持 `/plan`、`/goal` 和 `/review` 等斜杠命令。 用户无需一次性写对提示词，后续追问是预期调整方式。
OpenAI 已将其提示建议整合为一本面向日常用户而非开发者的指南。重点是四个构建模块、实用护栏和 Codex 工作流程，而不是 API 参数或模型调优。
该指南发布的时间正值 OpenAI 推出 ChatGPT Work：https://the-decoder.com/openai-admits-it-didnt-get-everything-quite-right-with-chatgpt-work-launch-and-scrambles-to-fix-ux-and-costs/，这是一个基于 Codex 技术和新 GPT-5.6 模型的独立产品，可在复杂项目上花费数小时，跨应用和文件操作，并生成完整的 Excel 或 Word 文档。
它在一个框架内涵盖了常规 ChatGPT 界面和 Codex，反映了两者正在融合为一个产品。其语气与 OpenAI 最近针对 GPT-5：https://the-decoder.com/prompting-gpt-5-for-agentic-workflows-and-advanced-coding-applications/ 和 GPT-5.5：https://the-decoder.com/openai-says-old-prompts-are-holding-gpt-5-5-back-and-developers-need-a-fresh-baseline/ 的开发者文档稍有不同，后者侧重于 API 参数、推理努力等级和复杂提示方案。终端用户指南放弃了这些内容，但保留了核心理念：从小开始，说出你的需求，仅在需要时添加规则。
OpenAI 将提示结构围绕目标、上下文、输出格式和边界进行设计。没有任何一项是必须的。公司表示，简短的提示通常有效，仅在较大任务时才需要填写全部四项。
指南建议以结果为先，而不是步骤序列。文档中写道：“只有在过程本身重要时才描述过程，否则要给 ChatGPT 留出空间去搜索、比较信息并调整其方法。”目标受众或格式对输出的影响远大于详细指令。
OpenAI 建议不要编写每一个步骤，而是设定一两条严格规则来阻止不希望出现的行为。示例：“保持批准的日期和预算数字不变”以及“将消息准备为草稿。不要发送。”
同样的“少即是多”逻辑也适用于上下文。只附上那些会真正影响答案的来源。指南将电子表格、PDF、图片、网页搜索和共享项目文件列为选项，同时提供插件：https://the-decoder.com/openai-expands-codex-with-role-specific-plugins-to-build-a-general-purpose-app-for-non-developers/ 用于 Google Drive、Gmail、Slack 和 GitHub。对于高风险工作，OpenAI 建议让 ChatGPT 验证自身输出，例如检查每个行动项是否都有负责人和截止日期。
指南区分了用于快速问题和改写的聊天（Chat）与用于整合多个来源、进行修改或生成如报告等较大成果的“工作”（Work）。工作任务消耗更多积分，但在节省时间或支持重要决策时价值更高。对于重复任务，OpenAI 建议先手动优化提示，然后再自动化。
用户不需要一次就完全准确提示。后续操作是完善输出的常规方式。跨会话的偏好设置应放在“设置 > 个性化”中的“自定义指令”。任何特定任务相关的内容都留在提示里。
对于编程助手 Codex：https://the-decoder.de/openais-gpt-5-3-codex-vereint-25-prozent-mehr-geschwindigkeit-mit-neuen-bestwerten-im-coding/，OpenAI 提出了两种在任务进行中影响任务的方法。“Steer” 会向当前运行添加消息并重定向它。“Queue” 则排队等待下一次运行发送消息。在命令行界面（CLI）中，Enter 和 Tab 可作为快捷键。
Codex 在沙箱环境中运行命令：https://the-decoder.de/openai-startet-codex-autonome-ki-agenten-fuer-softwareentwicklung/，限制文件和网络访问。如果任务需要超出这些限制，Codex 会请求批准。两个斜杠命令有助于多步骤项目：“/plan” 告诉 Codex 在修改前分析代码并提出方案，“/goal” 设定跨多个步骤 Codex 遵循的高层次目标。对于审查，用户可以在本地运行“/review”或者在 GitHub 评论中提到“@codex review”，可选关注点如“审查安全漏洞”。
保持 AI 动态更新。内容清晰、有用，无冗余。
关注 The Decoder 获取 AI 新闻、背景故事和专家分析。
The Decoder：https://the-decoder.com/
OpenAI has consolidated its prompting advice into a single guide written for everyday users, not developers. The focus is on four building blocks, practical guardrails, and Codex workflows rather than API parameters or model tuning.
The guide arrives shortly after OpenAI launched ChatGPT Work：https://the-decoder.com/openai-admits-it-didnt-get-everything-quite-right-with-chatgpt-work-launch-and-scrambles-to-fix-ux-and-costs/, a standalone product built on Codex technology and the new GPT-5.6 model that can spend hours on complex projects, operate across apps and files, and produce finished Excel or Word documents.
It covers both the regular ChatGPT interface and Codex in a single framework, reflecting how the two are converging into one product. The tone is a bit different from OpenAI's recent developer docs for GPT-5：https://the-decoder.com/prompting-gpt-5-for-agentic-workflows-and-advanced-coding-applications/ and GPT-5.5：https://the-decoder.com/openai-says-old-prompts-are-holding-gpt-5-5-back-and-developers-need-a-fresh-baseline/, which focused on API parameters, reasoning-effort levels, and elaborate prompt schemas. The end-user guide drops all of that but keeps the same core idea: start small, say what you want, and only add rules where you need them.
OpenAI structures prompts around a goal, context, output format, and boundaries . None are required. A short prompt often works, and filling in all four only makes sense for bigger tasks, the company says.
The guide recommends leading with the result, not a sequence of steps. "Describe a process when the process itself matters. Otherwise, leave ChatGPT room to search, compare information, and adjust its approach," the document reads. A target audience or format shapes the output far more than detailed instructions.
Rather than scripting every move, OpenAI recommends one or two hard rules to block unwanted behavior. Examples: "Keep the approved dates and budget figures unchanged" and "Prepare the message as a draft. Don't send it."
The same less-is-more logic applies to context. Only attach sources that will actually change the answer. The guide lists spreadsheets, PDFs, images, web search, and shared project files as options, along with plugins：https://the-decoder.com/openai-expands-codex-with-role-specific-plugins-to-build-a-general-purpose-app-for-non-developers/ for Google Drive, Gmail, Slack, and GitHub. For high-stakes work, OpenAI suggests asking ChatGPT to verify its own output, for instance, checking whether every action item has an owner and a deadline.
The guide draws a line between Chat for quick questions and rewording, and "Work" for tasks that pull in multiple sources, make changes, or produce larger deliverables like reports. Work tasks burn more credits but pay off when they save time or support important decisions. For recurring tasks, OpenAI suggests refining the prompt manually first, then automating it.
Users don't need to nail the first prompt. Follow-ups are the expected way to refine output. Preferences that carry across sessions belong in "Settings > Personalization" as "Custom Instructions." Anything task-specific stays in the prompt.
For the coding assistant Codex：https://the-decoder.de/openais-gpt-5-3-codex-vereint-25-prozent-mehr-geschwindigkeit-mit-neuen-bestwerten-im-coding/, OpenAI introduces two ways to influence tasks mid-run. "Steer" adds a message to the current run and redirects it. "Queue" lines up a message for the next one. In the CLI, Enter and Tab serve as shortcuts.
Codex runs commands inside a sandbox：https://the-decoder.de/openai-startet-codex-autonome-ki-agenten-fuer-softwareentwicklung/ that restricts file and network access. If a task needs to go beyond those limits, Codex asks for approval. Two slash commands help with multi-step projects: "/plan" tells Codex to analyze the code and propose an approach before making changes, while "/goal" sets a higher-level objective Codex follows across multiple steps. For reviews, users can run "/review" locally or mention "@codex review" in a GitHub comment, with an optional focus like "review for security vulnerabilities."
Stay in the loop on AI. Clear, useful, no fluff.
Follow The Decoder for AI news, background stories and expert analyses.
The Decoder：https://the-decoder.com/
扫码直达文章详情