These are the 40 prompts worth saving for Qwen3.7-Max, the flagship agent model released in May 2026 with a 1M-token context window that lets you paste huge documents or whole repos at once. They are grouped by job: reasoning, coding, writing, translation, research, business, data, and everyday tasks. Run them free at chat.qwen.ai or in the iOS and Android apps, or on the open-weight Qwen3 models you can self-host.

Every prompt is written out in full and ready to copy. They follow the Role + Task + Context + Constraints + Output format shape, and the golden rule with Qwen is simple: give it a hard problem plus rich context and turn on Thinking for the hard ones, so it shows its full chain-of-thought before answering. Leave the mode on Fast or Auto for quick drafting. New here? The guide to prompting Qwen for reasoning goes deeper, and the Qwen prompt cheat sheet is a handy one-pager. Swap anything in [BRACKETS] for your own details.

Advertisement

Reasoning & problem-solving

This is where Qwen's Thinking mode earns its keep. Turn it on and Qwen shows its full chain-of-thought before the answer, so you can audit the logic. Feed it the hard problem and rich context, then ask it to verify against the constraints before committing.

1. Reason through a hard decision

Switch to Thinking mode. I'm deciding between [OPTION A] and [OPTION B]. Context: [YOUR SITUATION, CONSTRAINTS, WHAT MATTERS MOST]. Work through it step by step: lay out the real trade-offs, the second-order consequences of each path, and the assumptions I might be wrong about. Then give a recommendation with a confidence level, and name the one piece of new information that would change your answer.

Why it works: Thinking mode exposes the reasoning so you can see where it agrees or disagrees with your gut instead of getting a black-box verdict.

2. Work a logic problem step by step

Switch to Thinking mode. Solve this problem and show every deduction: [PASTE PROBLEM]. Track the constraints as you go, state each inference and why it follows, and rule out options explicitly. Before the final answer, check that it satisfies every constraint in the problem. If more than one solution fits, say so and list them all.

Best for: Puzzles, riddles, and constraint problems where a wrong intermediate step ruins the answer.

3. Root-cause a stubborn problem

Switch to Thinking mode. Here's a problem I can't pin down: [DESCRIBE SYMPTOMS, WHAT YOU'VE TRIED, RELEVANT DATA OR LOGS]. Reason from symptoms to likely root causes. Rank the causes by probability, give the evidence for each, and tell me the single cheapest test to confirm or rule out the top one. Keep what you know separate from what you're inferring.

Why it works: Ranking causes by probability and naming the cheapest test turns vague reasoning into a concrete next move.

4. Stress-test a plan for flaws

Switch to Thinking mode. Here's my plan: [PASTE PLAN]. Act as a sharp skeptic. Work step by step through the ways this fails: hidden assumptions, weak links, single points of failure, and second-order effects I haven't considered. For each risk, rate likelihood and impact and suggest a concrete mitigation. Be blunt — I'd rather hear it now.

Best for: Pre-mortems on a launch, a project, or a big commitment before you're locked in.

5. Weigh options with a scored matrix

I'm choosing between these options: [LIST OPTIONS]. My criteria, most important first: [LIST CRITERIA]. Build a weighted decision matrix: score each option 1-5 on each criterion, apply the weights, and total them. Show the table, explain any score that isn't obvious, and give the winner. Then tell me which single criterion, if I've misjudged its weight, would flip the result.

Why it works: Forcing weights and a sensitivity check makes the decision explicit instead of a rationalized gut call.

Coding

Qwen3.7-Max is strong at code, and its 1M-token window means you can paste an entire module for context. Turn on Thinking for gnarly bugs, use Web Dev to generate whole apps, and reach for Qwen Code, the open-source CLI agent, in your terminal. For a deeper set, see the Qwen coding prompts.

6. Debug with a reasoning trace

Switch to Thinking mode. I'm getting this error in [LANGUAGE / FRAMEWORK version]: [PASTE ERROR]. Here's the relevant code: [PASTE CODE]. Reason through the likely root cause, give me the corrected code, and explain what was wrong in two sentences. If more than one cause is possible, rank them by likelihood, then verify your fix against the error before the final answer.

Why it works: Thinking mode spends real compute on the trace, which pays off on subtle bugs; the verify step catches confident-but-wrong fixes.

7. Explain unfamiliar code

Explain what this code does to a developer new to [LANGUAGE / LIBRARY]: [PASTE CODE OR ATTACH FILE]. Give a one-paragraph overview, then a block-by-block walkthrough of the tricky parts, and call out any bugs, edge cases, or performance concerns you notice. Skip the obvious lines and keep it concrete.

Best for: Onboarding to an unfamiliar codebase — paste the whole file; the 1M context handles it.

8. Write tests for a function

Write thorough unit tests for this function using [TEST FRAMEWORK]: [PASTE FUNCTION]. Cover the happy path, edge cases, invalid inputs, and boundary conditions. Explain in one line what each test verifies, and flag any behavior in the function that looks like a bug or is ambiguous enough to need a spec decision.

Why it works: Asking Qwen to flag ambiguous behavior surfaces spec gaps while it writes coverage.

9. Refactor without changing behavior

Refactor this code for readability and maintainability without changing behavior: [PASTE CODE]. Improve naming, reduce nesting, and extract logic where it helps. Return the refactored version, then a short bullet list of what you changed and why. Keep it idiomatic for [LANGUAGE] and don't add dependencies.

Best for: Cleaning up code you have to keep working in, safely enough to merge.

10. Build a feature or web app from a spec

Switch to Thinking mode. Build [FEATURE OR APP] in [LANGUAGE / STACK]. Requirements: [LIST REQUIREMENTS]. Constraints: [PERFORMANCE, DEPENDENCIES, STYLE]. First outline your approach and the key decisions, then write the full, runnable code with comments on the non-obvious parts. List your assumptions and how I'd test it. Verify the code meets each requirement before finishing. (For a full front end, use Web Dev to generate and preview it.)

Why it works: Outlining the approach first, then coding, catches design mistakes before they're buried in a wall of code; Web Dev turns the result into a live preview.

Writing & content

Give Qwen a Role, a clear Task, real Context, and an exact Output format, and it matches your tone closely. For drafting, leave it on Fast and let it write quickly; turn on Thinking only when the structure itself needs reasoning.

11. Blog post from an outline

You are a writer for [AUDIENCE]. Write a [1,200]-word blog post titled "[TITLE]" from this outline: [PASTE OUTLINE]. Keep the tone practical and direct, lead each section with the takeaway, use short paragraphs and concrete examples, and avoid clichés and filler. Output in clean Markdown with H2 sections and a two-line intro.

Best for: Turning a rough outline into a publishable draft that doesn't read like generic AI copy.

12. Rewrite for clarity and tone

Rewrite the text below to be clearer and more direct without losing meaning. Cut filler, fix weak verbs, and keep my key terms. Target a [confident but plain] tone at a [general professional] reading level. Return the rewrite first, then a short bullet list of the main changes. Text: [PASTE TEXT]

Why it works: Asking for the change list separately keeps the rewrite clean while still showing its work.

13. Cold email in your voice

You are writing a cold outreach email from me ([MY ROLE] at [MY COMPANY]) to [PROSPECT ROLE] at [PROSPECT COMPANY]. Goal: [GOAL]. Keep it under 90 words, open with a specific reason I'm reaching out to them (not a template), state one clear value point, and end with a low-friction ask. Give me three subject-line options.

Best for: Outreach that reads like a person wrote it, with subject lines you can A/B test.

14. Headline and hook variations

Generate 12 headline options for [PIECE / PRODUCT] aimed at [AUDIENCE]. Mix angles: benefit-led, curiosity, contrarian, number-led, and how-to. Keep each under 65 characters, avoid hype words, and label the angle of each. Then pick your top three and say why they'd perform best.

Why it works: Mixing labeled angles gives you a batch of testable headlines with the reasoning attached.

15. Story or scene draft

Write a [500]-word [genre] scene. Setup: [WHO, WHERE, WHAT'S AT STAKE]. Point of view: [FIRST / THIRD], tense: [PAST / PRESENT]. Show, don't tell; let the tension build through action and dialogue rather than narration; end on a beat that pulls the reader forward. Match this voice: [DESCRIBE OR PASTE A SAMPLE]. Avoid clichés and purple prose.

Best for: Fiction drafting when you want a scene that moves instead of a summary of one.

Advertisement

Translation & languages

Multilingual is a Qwen strength — 100+ languages, especially strong Chinese ⇄ English and other Asian languages, with a specialized Qwen-MT model covering about 92 languages. Give it the tone and audience, not just the words, and it localizes rather than translates literally.

16. Translate while preserving tone

Translate the text below from [SOURCE LANGUAGE] into [TARGET LANGUAGE]. Preserve the tone and register ([e.g. formal, warm, marketing]), keep names, product terms, and numbers exact, and adapt idioms so they read naturally to a native speaker rather than translating them word for word. Return the translation, then flag any phrase where a choice was tricky and give an alternative. Text: [PASTE TEXT]

Why it works: Asking Qwen to flag tricky choices surfaces the spots where a literal translation would have sounded off.

17. Localize copy for a market

Localize this copy for [TARGET MARKET / LOCALE], don't just translate it. Adapt currency, units, date formats, examples, and cultural references so it feels native to [TARGET LANGUAGE] readers in that market. Keep the brand voice [DESCRIBE]. Return the localized version, then a short note on what you changed for the market and why. Copy: [PASTE COPY]

Best for: Adapting landing pages, ads, or app strings so they land in a new market instead of reading like a translation.

18. Build a bilingual glossary

Build a bilingual glossary for [DOMAIN — e.g. fintech, medical devices] between [LANGUAGE A] and [LANGUAGE B]. Extract the key terms from this material: [PASTE OR ATTACH SOURCE]. For each term give: term in A, preferred term in B, a one-line definition, and a usage note or common mistranslation to avoid. Output as a table and keep the preferred terms consistent for reuse.

Why it works: A consistent, defined term list keeps every later translation on-message instead of drifting term by term.

19. Translate and time subtitles

Translate these subtitles from [SOURCE LANGUAGE] into [TARGET LANGUAGE], keeping the SRT timestamps unchanged: [PASTE SRT]. Keep each line short enough to read on screen (aim for [42] characters per line, max two lines), preserve the speaker's tone, and split or condense lines so the timing still works. Return valid SRT.

Best for: Subtitling video where the translation has to fit real reading time and keep its cues.

20. Polish non-native English

I wrote this in English as a non-native speaker. Polish it to sound natural and fluent while keeping my meaning and voice — don't make it more formal than it needs to be. Fix grammar, word choice, and awkward phrasing. Return the polished version, then a short list of the recurring mistakes so I can learn them. Text: [PASTE TEXT]

Why it works: The recurring-mistakes list turns each edit into a lesson, so your next draft needs less fixing.

Research & analysis

For a big job, use Deep Research: Qwen autonomously searches many sources, resolves conflicts, and returns a structured, cited report. For quick current facts, flip on Web Search and demand links. For documents, upload a PDF or DOCX — the 1M window reads the whole thing. More in the Qwen research prompts and the roundup at /best-qwen-prompts.

21. Deep Research report

Run Deep Research on [TOPIC / QUESTION]. I need a structured report covering: the current state, the main viewpoints and who holds them, the key data and where it comes from, and where things are heading. Resolve conflicts between sources and say which side the evidence favors. Cite every source with a link and note the date. End with what's still uncertain and the open questions worth watching.

Why it works: Deep Research does the multi-source legwork and conflict resolution itself, returning a cited report you can turn into a webpage or podcast.

22. Cited web brief with Web Search

Turn on Web Search. Research [TOPIC / QUESTION] and write me a brief as of this month. Cover the current state, the main viewpoints, and where things are heading. Cite every source with a link, prefer primary and recent sources, and put the publication date next to each fact. End with what's still uncertain or contested.

Best for: A current, checkable brief instead of an answer from the training cutoff.

23. Compare sources and find the gap

Turn on Web Search. Find the main sources on [QUESTION] and compare what they say. Build a table: Source | Key claim | Evidence given | Date | Link. Then tell me where the sources agree, where they conflict, and which claim is best supported. Flag any source that looks weak or out of date. Cite every source with a link.

Why it works: A comparison table across live sources surfaces disagreement that a single blended summary would hide.

24. Summarize a large uploaded document

I've attached a document. Read it in full, then give me: a 3-sentence summary, the 5 most important points as bullets, any conclusions or recommendations it makes, and anything it leaves unanswered or assumes without evidence. Ground every point in the document only; if something isn't in it, say so rather than filling the gap.

Best for: Long reports, contracts, or papers — the 1M-token window lets Qwen hold the whole file at once.

25. Fact-check a claim with Web Search

Turn on Web Search. Fact-check this claim: "[CLAIM]". Find the original source, what the primary evidence actually says, and how credible outlets have covered it. Rate it True / Misleading / False / Unproven with a short reason. Cite every source with a link, and separate what's confirmed from what's still uncertain.

Why it works: Web Search plus a required rating and links turns a vague "is this true?" into an auditable verdict.

Business & work

Give Qwen your real context and it handles the structure. Turn on Thinking for strategy calls with real trade-offs; leave it off for straightforward drafting and formatting.

26. Meeting notes to action items

Turn these meeting notes into a clean summary: [PASTE NOTES]. Output three sections: Decisions made, Action items (as a table with Owner, Task, Due date), and Open questions. Keep it tight, don't invent details that aren't in the notes, and flag anything left unresolved.

Why it works: The owner/task/due table turns a wall of notes into something the team can actually track.

27. One-page business plan

You are a pragmatic startup advisor. Draft a one-page plan for this idea: [DESCRIBE IDEA]. Cover: the problem, the target customer, the offer, how it makes money, the first three steps to validate it cheaply, and the biggest risk. Be blunt about weaknesses. Output as clear sections, no filler.

Best for: Pressure-testing an idea before you sink time into it. The "be blunt" line matters.

28. Strategy memo with Thinking

Switch to Thinking mode. Write a one-page strategy memo on [DECISION / QUESTION]. Context: [BACKGROUND, GOALS, CONSTRAINTS, DATA]. Lay out 2-3 real options, the trade-offs of each, and a clear recommendation with the reasoning. Name the key assumption the recommendation rests on and what would have to be true for it to hold. Keep it tight and executive-ready.

Best for: A memo that names the trade-offs honestly instead of arguing for a foregone conclusion.

29. Prioritized weekly plan

Here's everything on my plate this week: [PASTE LIST]. Act as a sharp chief of staff. Sort it by impact and urgency, tell me the three things that actually move the needle, what to delegate or drop, and lay it out as a simple day-by-day plan. Call out anything that looks like busywork.

Why it works: The chief-of-staff framing pushes Qwen to cut, not just organize, an overwhelming list.

30. Write a job description

Write a job description for a [ROLE] at [COMPANY / TYPE OF COMPANY]. Context: [TEAM, LEVEL, KEY RESPONSIBILITIES, MUST-HAVE SKILLS, LOCATION / REMOTE]. Keep it concrete and honest about the day-to-day, avoid buzzwords and inflated requirements, and separate must-haves from nice-to-haves. Output: a two-line summary, Responsibilities, Requirements, and What we offer. Keep it under 400 words.

Best for: A posting that attracts the right people instead of a generic list of every skill imaginable.

Data & spreadsheets

Qwen's Code Interpreter runs Python inside the chat: upload a CSV and it can analyze, compute statistics, clean the data, and draw charts. State your columns and the question, and ask it to show both the result and the code it ran.

31. Analyze an uploaded CSV

I've attached a CSV. Use Code Interpreter to analyze it. First describe the columns and row count, then answer: [YOUR QUESTIONS — e.g. what drives [METRIC], top segments, trends over time]. Show the key numbers in a table, note anything surprising or any data-quality issues you hit, and include the Python you ran so I can reproduce it.

Why it works: Running real Python on your file gives grounded numbers, and returning the code makes the analysis reproducible instead of a guess.

32. Spreadsheet formula and model

I need a [Google Sheets / Excel] formula to [GOAL]. My data is laid out like this: [DESCRIBE COLUMNS]. Give me the formula, explain what each part does, and note common ways it could break (blank cells, text vs numbers, ranges that grow). If a small helper column would make it cleaner, suggest it.

Why it works: The explanation plus gotchas means you can maintain the sheet yourself instead of pasting a formula you don't understand.

33. Build a chart from data

Using Code Interpreter, make a chart from the attached data. I want to show [WHAT YOU WANT TO COMMUNICATE — e.g. the trend in X by month]. Pick the chart type that fits, label the axes and units clearly, and keep it clean. Then tell me in one or two sentences what the chart shows and any caveat I should mention when I present it.

Best for: Turning a raw file into a labeled chart plus a plain-English takeaway you can drop into a deck.

34. Run a statistical test

Switch to Thinking mode and use Code Interpreter. With the attached data, I want to know whether [HYPOTHESIS — e.g. group A differs from group B on [METRIC]]. Choose the right statistical test and say why it fits, state the assumptions and check them, run it, and report the result with the effect size and a plain-English interpretation. Flag anything that would make the result unreliable.

Why it works: Thinking mode picks and justifies the test while Code Interpreter runs it, so you get a defensible result instead of a p-value with no context.

35. Clean a messy dataset

Use Code Interpreter to clean the attached dataset. Handle: missing values, duplicates, inconsistent formats (dates, casing, units), and obvious outliers. Tell me each decision you made and why before you apply it, don't drop data silently, and return the cleaned file plus a short changelog of what you fixed and how many rows it touched.

Best for: Prepping a raw export for analysis without hand-editing every cell — with a changelog so the cleaning is auditable.

Everyday & personal

Qwen is free and handles everyday planning and drafting well. Give it your real constraints, and turn on Web Search when the task needs current prices, hours, or availability.

36. Plan a trip with Web Search

Turn on Web Search. Plan a [NUMBER]-day trip to [DESTINATION] for [WHO] with a budget of [BUDGET]. We like [INTERESTS] and want to avoid [DISLIKES]. Give a day-by-day itinerary with realistic timing, group nearby stops to cut travel, and note current prices and opening hours where you can with links. Add one rainy-day backup and one splurge option.

Why it works: Grouping stops by location and adding a backup makes the itinerary usable in the real world, not just a wish list.

37. Meal plan from what you have

I have these ingredients: [LIST]. Plan [NUMBER] meals for [PEOPLE] using mostly what I have, adding as few new items as possible. For each meal give a short ingredient list, quick steps, and rough time. Respect these needs: [DIET / ALLERGIES / DISLIKES]. At the end, give me a short shopping list of only the extras I'd need.

Best for: Using up what's in the fridge without a separate grocery run.

38. Draft a difficult message

Help me write a message to [WHO] about [SITUATION]. My goal is [GOAL] and I want to sound [TONE — e.g. firm but kind]. Keep it honest and clear, don't over-apologize or ramble, and leave the door open for a good response. Give me two versions: a shorter one and a slightly warmer one. Context they'll need: [BACKGROUND].

Why it works: Two versions let you pick the tone that fits, and naming the goal keeps the message from wandering.

39. Learn a hard concept

Explain [CONCEPT] to me. First give the one-sentence core idea, then build it up with a concrete everyday analogy, then a worked example, then the common misconception people have. Assume I know [YOUR CURRENT LEVEL]. End with two questions I could answer to check I actually understood it.

Best for: Getting past a concept that a textbook explained badly — turn on Thinking if it needs to work an example with you.

40. Budget and money check-up

Switch to Thinking mode. Here's my monthly income and spending: [PASTE NUMBERS OR CATEGORIES]. My goal is [GOAL — e.g. save X, pay down debt]. Analyze where the money goes, flag the categories that look high for my goal, and suggest a realistic adjusted budget with specific numbers. Show your reasoning and don't recommend cuts too painful to stick to. This is general guidance, not financial advice.

Best for: A grounded look at your spending with realistic, stickable changes.

Want the shortest possible reference for all of this? The Qwen prompt cheat sheet lists every mode and modifier on one page, and bookmark this roundup at /best-qwen-prompts for the full set.

Frequently Asked Questions

Which Qwen model are these prompts built for?

They target Qwen3.7-Max, the flagship agent model released in May 2026, with a 1M-token context window so you can paste huge documents or whole repos. They also work on Qwen-Plus and Qwen-Flash and the open-weight Qwen3 models, since Thinking mode, Web Search, Deep Research, and file upload are shared features of Qwen Chat.

What is Thinking mode and when should I use it?

Thinking mode is Qwen's deep-reasoning toggle. Turn it on and Qwen shows its full chain-of-thought before the final answer. Use it for hard math, logic, debugging, and strategy where accuracy or an auditable trace matters. Leave the mode on Auto to let Qwen decide, or on Fast for instant drafting with no reasoning tokens.

How do I turn on Web Search or Deep Research in Qwen?

In Qwen Chat, flip the Web Search toggle before you send a prompt to pull in real-time results, and ask Qwen to cite each source with a link. For a bigger job, switch to Deep Research: Qwen autonomously searches many sources, resolves conflicts, and returns a structured, cited report, which you can turn into a hosted webpage or a podcast.

What is the prompt formula for Qwen?

Role + Task + Context + Constraints + Output format. Tell Qwen who it is, what to do, the background it needs, the limits, and the exact shape of the answer. The golden rule: give it a hard problem plus rich context and turn on Thinking for the hard ones; leave it on Fast or Auto for quick drafting.

Is Qwen free and open-source?

Yes. Qwen Chat is free at chat.qwen.ai and in the iOS and Android apps. The open-weight Qwen3 models are on Hugging Face and GitHub under the Apache 2.0 license, so you can self-host or build on them. The proprietary flagship Qwen3.7-Max runs in Qwen Chat and via API.

Can Qwen read my files, and how big can they be?

Yes. Attach a PDF, DOCX, TXT, or image and Qwen reads the whole document. Because Qwen3.7-Max has a 1M-token context window, you can paste or upload very large files — long contracts, research papers, or an entire codebase — and ask questions grounded in the full text at once.

What can Code Interpreter and Web Dev do?

Code Interpreter runs Python inside Qwen Chat to analyze uploaded CSVs, compute statistics, clean data, and build charts. Web Dev generates full websites and apps from a natural-language prompt, and Qwen Code is an open-source command-line coding agent that works across scaffolds, comparable to Claude Code.

How do the [BRACKET] placeholders work?

Anything in square brackets is a swap-in. Replace [TOPIC], [PASTE CODE], or [GOAL] with your own details before sending. The rest of each prompt is written to be copy-paste ready.

Advertisement