Qwen prompt builder in Alibaba's official framework: background, purpose, style, tone, audience, output, plus steps, ### delimiters and reasoning.
Qwen Prompt Builder
Write a prompt in the framework from Alibaba Cloud's official guide for Qwen: background, purpose, style, tone, audience and output.
How to write a Qwen prompt here
Start with the purpose and the background
The purpose is the task you want done; the background is what the model needs to know. In the guide's own example, the same request with background, style, tone and audience added produced output aimed at its readers.
Add style, tone, audience and output
Style can be a kind of expert or a genre; tone is formal, playful, warm and so on; audience says who it is for; output fixes the form, such as a list, JSON or a report. Empty fields stay out of the prompt.
Use the techniques on hard tasks
Steps you list become a numbered #Steps# block; long material is split into paragraphs between ### lines; "reason first" adds an instruction to write the reasoning before the conclusion.
Copy, test, revise
The guide treats prompting as testing and iterating. Run it once, see what is off, and change the field that controls it.
Where the framework comes from
Alibaba Cloud Model Studio's text-generation prompt guide splits a good prompt into six parts: background, purpose, style, tone, audience and output, each written as a labelled block such as #背景#. The guide compares the same promotional request both ways: one sentence gave output it calls too generic, while the framework, with style, tone and audience added, produced copy aimed at its young readers.
The guide adds four techniques: give an example of the output you want; set out the steps; separate units with rare markers such as ### or ===; and have the model reason before it concludes. The last three are optional fields here, and the example has its own field.
This page used to be a generic form (role, task, context, code, tools, format, constraints, examples), the same as eight other builders, with nothing from Alibaba's guide in it.
Frequently Asked Questions
From Alibaba Cloud Model Studio's text-generation prompt guide, written for its Qwen models. Its recommended framework has six parts (background, purpose, style, tone, audience, output), each written as a label such as #背景#. Steps, delimiters and asking for reasoning are three more techniques from the same guide.
That is how the guide's own examples are written: each part opens with a #label#. Clear separation helps the model tell the background from the requirements. The guide also says the framework can grow or shrink with the task, so empty parts are dropped.
You can paste it into any chat model, but the guide cited here is Alibaba's, written for Qwen. Other vendors' guides are not cited on this page.
No. The prompt is put together in your browser. No model is called and nothing is sent anywhere.
Method & sources
How it computes
In the browser, by a tested kernel: the six-part framework of Alibaba Cloud's 文生文Prompt指南 (背景, 目的, 风格, 语气, 受众, 输出), each a #label# block, empty ones left out; optional #任务步骤# numbered, material split by ### delimiters, an output example, and an instruction to reason before concluding, all four from the same guide. No model is called.
What this tool implements
- Checked 2026-10-21: Qwen is Alibaba's model family (its consumer app is now branded 千问), and Alibaba Cloud Model Studio documents function calling for Qwen, matching the page's function / tool-calling field. No errors found; the prompting advice is general practice, not attributed to Alibaba.
- Rebuilt 2026-11-04 in all three languages. The page was a generic role / goal / context / code / tools / format form, the same as eight other builders, and its 2026-10-21 check said its prompting advice was general practice, not Alibaba's. It now writes the framework Alibaba's own text-generation guide recommends for Qwen, labelled the way the guide labels it (#背景#), with the guide's four techniques as options.
- The code-task and function-calling fields were removed with the copy and titles that advertised them: function calling is an API feature, not a part of a prompt, and the guide cited here does not treat it. The Function calling source was removed with them.
- Merged 2026-11-04: /chinese-llm-prompt-builder/ now redirects here. It was a generic role / goal / context / audience / tone / format / constraints / examples form, and each of those fits one of this page's framework blocks; it held no list or data to port.
Sources
- Qwen: Alibaba's assistant site, 「千问是阿里官方AI助手，提供最强Qwen大模型体验的第一入口」. https://www.qianwen.com/
- Tongyi Lab (通义实验室), Alibaba: model family overview. https://tongyi.aliyun.com/
- Alibaba Cloud Model Studio. 文生文Prompt指南: the Prompt 框架 (背景, 目的, 风格, 语气, 受众, 输出) and its four techniques (output examples, task steps, delimiters such as ###, guiding the model to think). https://help.aliyun.com/zh/model-studio/prompt-engineering-guide — read 2026-11-04.
Pick up where you left off
Stored only in this browser — never sent to our servers.