Guide · ChatGPT
The Best ChatGPT Prompts
A curated, copy-ready library of the highest-leverage ChatGPT prompts — organized by use case and tested across GPT-4o and GPT-5.
PromptInFlow AI Guides
General AI Models
Image & Video Models
AI Task Guides
- AI WritingRead guide
- AI MarketingRead guide
- AI CodingComing soon
- AI BusinessComing soon
- AI EducationComing soon
Most people get mediocre answers from ChatGPT not because the model is weak, but because the prompt is. A one-line request like "write me a sales email" forces ChatGPT to guess at audience, tone, offer, length and format — and when a model has to guess, it defaults to the safest, blandest, most generic option. The prompts in this guide remove that guesswork. They tell ChatGPT exactly who it is, what you want, who it's for, and what the output should look like — so the first draft is usable, not a starting point you have to rewrite.
This is a working reference, not a listicle. Every prompt has been tested on the current ChatGPT lineup (GPT-4o and GPT-5), grouped by the job you're trying to get done, and written with clear {placeholders} so you can adapt them to your own brand, audience and tone in seconds. You'll find prompts for writing and editing, marketing and SEO, business strategy, coding and code review, education, and creative work — plus the prompt-engineering principles that make them work, so you can write your own when none of ours fit.
Who is this guide for? Founders and operators who want ChatGPT to act as a senior teammate instead of a faster intern. Marketers and writers who need on-brand drafts without an hour of cleanup. Developers who use ChatGPT as a pair programmer. Educators, consultants and creators who want repeatable prompt recipes they can run weekly. If you've ever closed a ChatGPT tab thinking "that's not quite right" and didn't know how to fix it, this guide is for you.
To get the best results, treat each prompt as a template, not a script. Replace every {placeholder} with something specific — "B2B SaaS founders evaluating CRM tools" beats "business owners" every time. Run the prompt in a fresh chat so prior context doesn't bleed in. Read the first output, then ask one focused follow-up ("make the tone more direct," "cut to 120 words," "add a stronger CTA") instead of rewriting the original prompt from scratch. And bookmark this page — we refresh it whenever a new ChatGPT version ships or a prompt stops performing.
Editorial standards
How we selected these prompts
Why each prompt earns its place in the library.
Every prompt in this guide earns its place. We don't aim for the longest list on the internet — we aim for the one you'll actually keep open in a tab. Prompts are sourced from our own day-to-day work, real workflows shared by builders and marketers in the Prompt InFlow community, and structured prompt-engineering patterns that hold up across model releases. Before a prompt ships into the library, it has to clear a short checklist: produce a usable first draft without follow-up, work on a fresh chat with no prior context, and adapt cleanly to a different audience or brand with only the {placeholders} changed.
Clarity
The intent is obvious in the first two lines. No buried instructions, no contradictory constraints, no jargon that forces the model to guess what you mean.
Adaptability
Every prompt uses explicit {placeholders} so the same template works for a solo consultant, a Series B startup or an enterprise team — change five words, keep the structure.
Practical usefulness
We only include prompts that solve a real recurring task — drafting a cold email, building an SEO outline, reviewing a pull request — not novelty prompts that demo well and never get used twice.
Quality over quantity
We'd rather publish 50 prompts you'll reuse weekly than 500 you'll scroll past. If two prompts overlap, the weaker one gets cut.
Who this guide is for
This guide is built for anyone who wants ChatGPT to do real work — not just answer trivia.
Beginners
Learning prompt engineering from scratch and looking for proven patterns to copy.
Content creators
Writers, newsletter authors and YouTubers who need on-brand drafts in minutes.
Marketers
Ad copy, landing pages, SEO briefs and email sequences mapped to a funnel stage.
Developers
Using ChatGPT as a pair programmer for reviews, refactors, tests and debugging.
Business professionals
Founders, operators and consultants drafting strategy memos, SOPs and decks.
Students & educators
Explainers, study plans, lesson outlines and feedback loops for faster learning.
In this guide
What you'll learn
Skim the highlights, then jump to the section you need.
The anatomy of a high-leverage prompt
The six components every ChatGPT prompt should include — role, goal, context, constraints, output format and examples.
50+ copy-ready prompts by use case
Writing, marketing, coding, business, education and creative prompts you can paste into ChatGPT and run today.
How to adapt any prompt to your brand
A simple variable-replacement workflow so the same prompt works for any company, audience or tone.
Common mistakes that kill output quality
The patterns that make ChatGPT produce generic, hallucinated or off-brand answers — and how to avoid them.
Framework
How great prompts work
The six-part anatomy behind every prompt that consistently ships usable output.
Every prompt that consistently produces usable output — across industries, tones and model versions — shares the same underlying structure. Once you can see the parts, you can build your own prompts as quickly as you can think them. We call it the R-G-C-C-O-E framework: Role, Goal, Context, Constraints, Output format, Examples.
Role
Tell ChatGPT who it is. "You are a senior B2B copywriter" narrows vocabulary and raises the quality bar before the model writes a single word. Roles beat adjectives — "act as a fractional CFO" produces sharper financial analysis than "write a financial analysis."
Goal
State the outcome in one sentence. "Write a cold email that books a 15-minute discovery call" is a goal. "Write a sales email" is a wish. A clear goal lets the model optimize the right metric — clicks, replies, comprehension, conversions.
Context
Give ChatGPT the background it would need if it were a new contractor: who the audience is, what the product does, what's been tried before, and what you've already ruled out. Two sentences of real context outperforms ten adjectives.
Constraints
List what's off-limits and what's required: tone ("direct, no hype"), length ("under 120 words"), platform ("LinkedIn post"), banned phrases ("no 'in today's fast-paced world'"). Constraints are the single biggest lever for on-brand output.
Output format
Spell out the shape of the answer: "Return as: subject line, body in three short paragraphs, single-sentence CTA, two alternate subject lines." When the format is explicit, the model stops improvising structure and focuses on substance.
Examples
When tone or style matters, paste one or two examples of what "good" looks like and one of what to avoid. Few-shot examples are the fastest way to teach ChatGPT your brand voice without writing a 500-word style guide.
Three examples — and why they work
Cold outbound email
You are a senior B2B copywriter. Write a cold email to {audience: heads of RevOps at 50–500-person SaaS companies} for {product: a pipeline-hygiene tool that auto-cleans Salesforce data}. Goal: book a 15-minute discovery call. Tone: direct, no hype, no "hope you're well." Constraints: under 110 words, one specific pain point, one proof point, one CTA. Output: subject line, body, two alternate subject lines.SEO article outline
You are an SEO content strategist. Build a long-form article outline for the keyword "best CRM for solopreneurs." Search intent: commercial investigation. Audience: solo consultants and freelancers. Output: H1, meta description (≤155 chars), 6–8 H2s with one-line summaries, FAQ block with 5 questions matching real Google PAA queries. Do not include intro fluff in the outline.
Code review pass
You are a staff engineer doing a PR review. Review the function below for correctness, edge cases, readability and performance — in that priority order. Constraints: cite line numbers, suggest concrete fixes (not vague advice), flag anything that would block merge. Output: a bulleted list grouped by severity (blocker, nit, optional). Function: {paste code}.Browse by use case
Featured prompt categories
Jump into the library that matches what you're working on — each category includes guidance on when to use it and what good output looks like.
- When to use
- Reach for writing prompts when you need a first draft fast — articles, emails, scripts, social posts, internal memos — and the cost of a blank page is higher than the cost of editing.
- What you can achieve
- On-brand drafts in minutes, consistent tone across long pieces, ghostwritten LinkedIn posts that don't read like AI, and rewrites that match a reference voice you paste in.
- Best practices
- Always specify audience, tone and length — ChatGPT defaults to "general adult, neutral, ~500 words" when you don't.
- Paste 1–2 examples of your real writing as voice references; few-shot examples beat any "write like me" instruction.
- Ask for the structure first (outline, headers), approve it, then expand — it's faster than rewriting a full draft.
- When to use
- Use marketing prompts for ad copy, landing pages, SEO briefs, email sequences and campaign concepts — anything where you need conversion-aware copy at volume.
- What you can achieve
- Tested ad variants for A/B tests, full landing-page copy from a single brief, keyword clusters and content briefs, and email sequences mapped to a funnel stage.
- Best practices
- Name the offer, audience and funnel stage explicitly — "TOFU blog reader" produces different copy than "BOFU demo request."
- Ask for 3 variants max per request; quality drops sharply past three.
- Include the one objection you most need to overcome — it's the single biggest lever on conversion copy.
- When to use
- Use coding prompts for debugging, refactors, code reviews, test generation, architecture sketches and translating between languages or frameworks.
- What you can achieve
- PR-quality reviews, regression-safe refactors, edge-case unit tests, and architecture trade-off analyses you can take into a design doc.
- Best practices
- Paste the smallest reproducing snippet, not the whole file — ChatGPT reasons better about focused code.
- State the runtime, language version and constraints up front ("Node 20, TypeScript strict, no new dependencies").
- Ask for tests alongside any non-trivial fix; a fix without a test is a regression waiting to happen.
- When to use
- Use business prompts for strategy memos, financial analysis, competitor breakdowns, sales decks, hiring scorecards and operational SOPs.
- What you can achieve
- First-draft strategy docs that surface trade-offs, sanity-checked financial models, structured competitive teardowns, and SOPs your team can actually follow.
- Best practices
- Give the model your actual numbers, not hypotheticals — ChatGPT analyzes specifics far better than abstractions.
- Ask for the counter-argument: "steelman the opposing view" surfaces blind spots faster than asking for risks.
- Request decision-ready output (recommendation + rationale + open questions), not exhaustive analysis.
Hand-picked
Curated prompts
The prompts we reach for most often — copy, paste, adapt.
High-Converting Cold Sales Email
Write a 4-line cold outreach email with a personalized hook, value prop, social proof and soft CTA.
You are a B2B sales copywriter. Write a 4-sentence cold email to {persona} at {company}. Open with a specific observation about {trigger_event}, then connect it to {value_prop}. Include one short social proof line and a low-friction CTA.
SEO Topic Cluster Builder
Generate a pillar page plus 12 supporting article ideas with target keywords and search intent.
Act as an SEO strategist. For the seed topic {topic}, produce one pillar page idea and 12 supporting articles. For each: working title, primary keyword, search intent, and one internal link target.
Senior Engineer Code Review
Get a staff-engineer-grade review of a diff with risk callouts, simpler alternatives and test gaps.
You are a staff engineer. Review this diff and return: (1) correctness risks, (2) simpler alternatives, (3) missing tests, (4) one nit. Be specific. Diff: {diff}
At a glance
Quick reference tables
Cheat-sheets for picking the right model and the right prompt style.
ChatGPT models at a glance
Pick the model that fits the job — not the newest one by default.
| Model | Best for | Watch out for |
|---|---|---|
| GPT-5 | Complex reasoning, long context, multi-step agents | Slower and more expensive per token |
| GPT-4o | Daily writing, marketing, coding, multimodal tasks | Occasionally over-edits well-written input |
| GPT-4o mini | High-volume, low-stakes tasks (tagging, classification, short replies) | Weaker at long-form reasoning and nuance |
| o-series (reasoning) | Math, logic, code-heavy debugging, structured planning | Verbose; not ideal for short-form copy |
Prompt styles and when to use each
| Style | Use when | Example trigger |
|---|---|---|
| Zero-shot | The task is common and well-defined | "Summarize this article in 5 bullets." |
| Few-shot (with examples) | Tone, format or style matters | "Here are 2 examples of our voice — match them." |
| Chain-of-thought | The task needs reasoning, not recall | "Think step by step before answering." |
| Role + constraints | You need on-brand, conversion-aware output | "You are a senior copywriter. Constraints: …" |
Method
How to write better prompts
Four habits that lift the quality of every prompt you write.
Lead with a role
Start with 'You are a senior {role}…'. Giving ChatGPT a persona narrows its vocabulary, raises the quality bar and removes the need to over-explain context.
Replace every placeholder
Vague inputs produce vague outputs. Before you hit send, swap every {placeholder} for a concrete value — audience, tone, offer, constraint.
Specify the output format
Tell ChatGPT exactly what you want back: subject line, three short paragraphs, a CTA, two alternates. Format instructions are the single biggest quality lever.
Iterate, don't rewrite
Get the structure right first, then ask follow-up messages to refine tone, length or angle. Editing inside the original prompt is slower and noisier.
Avoid
Common mistakes
The patterns that quietly tank output quality.
- Asking a single open-ended question with no role, audience or format — ChatGPT optimizes for the wrong thing.
- Leaving generic placeholders like {audience} unchanged in the prompt.
- Requesting 10 variants at once — quality drops sharply after 3.
- Skipping constraints (length, tone, platform) and then complaining the output is off-brand.
- Treating the first draft as the final draft instead of running one critique-and-rewrite pass.
- Stacking unrelated tasks into one prompt — separate chats outperform mega-prompts for unrelated jobs.
FAQ
Frequently asked questions
Quick answers about this guide and the prompts in it.
Keep reading
Related guides
The Best Claude Prompts
A curated, copy-ready library of the highest-leverage Claude prompts — engineered for Claude's strengths in long-context reasoning, careful writing and structured analysis.
The Best Gemini Prompts
A curated, copy-ready library of the highest-leverage Google Gemini prompts — built around Gemini's strengths in multimodal reasoning, massive context and live Google data.
The Best AI Writing Prompts
Frameworks, model picks and copy-ready prompts for every writing task — from blog posts and emails to SEO content, product copy and storytelling.
The Best AI Marketing Prompts
A curated, model-aware library of marketing prompts that ship — built for the channels and tasks marketers actually run every week.
Explore
Related categories
Compatible models
Works well with
Fresh
Latest prompts
Recently added to the Prompt InFlow library.
High-Converting Cold Sales Email
Write a 4-line cold outreach email with a personalized hook, value prop, social proof and soft CTA.
You are a B2B sales copywriter. Write a 4-sentence cold email to {persona} at {company}. Open with a specific observation about {trigger_event}, then connect it to {value_prop}. Include one short social proof line and a low-friction CTA.
SEO Topic Cluster Builder
Generate a pillar page plus 12 supporting article ideas with target keywords and search intent.
Act as an SEO strategist. For the seed topic {topic}, produce one pillar page idea and 12 supporting articles. For each: working title, primary keyword, search intent, and one internal link target.
Senior Engineer Code Review
Get a staff-engineer-grade review of a diff with risk callouts, simpler alternatives and test gaps.
You are a staff engineer. Review this diff and return: (1) correctness risks, (2) simpler alternatives, (3) missing tests, (4) one nit. Be specific. Diff: {diff}
Veo Character Consistency Sheet
Keep the same character across multiple Veo shots with a reusable description block and shot list.
Character: 32-year-old woman, shoulder-length auburn hair, freckles, olive linen jacket. Reuse this exact description for every shot. Shot 1: medium close-up, golden hour. Shot 2: walking shot, overcast street. Shot 3: cafe interior, warm tungsten.
In summary
Conclusion
The ideas to carry forward — and where to go next.
If there's one idea to carry out of this guide, it's this: great prompts aren't magic incantations — they're clear briefs. The prompts that consistently produce usable output give ChatGPT a role, a goal, the context it needs, the constraints it has to respect, and the exact shape of the answer. Skip any of those and the model fills the gap by averaging the internet, which is rarely what you want.
Treat every prompt in this library as a starting point, not a finished script. Copy it, replace the {placeholders} with something specific to your audience and offer, run it in a fresh chat, then iterate with short follow-ups instead of rewriting from scratch. The difference between a beginner and an expert prompter isn't a secret prompt — it's the willingness to refine the same prompt three times instead of giving up after one.
Prompt engineering is a skill, and like every skill it compounds with reps. The more prompts you write, ship and refine, the faster you'll recognize which lever — role, constraint, format, example — to pull when an output misses. When you're ready for more, dig into our other guides, browse the full prompt library by use case, or open one of our generators to build a custom prompt in seconds.
Continue Learning
Prompt Engineering Learning Path
A guided reading order through every Prompt InFlow flagship guide — start with the model you use most, then layer in topical skills.
- 1You are here
Best ChatGPT Prompts
50+ tested ChatGPT prompts and the R-G-C-C-O-E framework that makes them ship usable output.
Model guide - 2
Best Claude Prompts
Long-context reasoning, on-voice writing and XML-tagged briefs for Claude 3.5 and Claude 4.
Model guide - 3
Best Gemini Prompts
Grounded, multimodal and long-context prompts that lean into Gemini's real-time strengths.
Model guide - 4
Best AI Writing Prompts
Voice, structure and editing — the writing playbook across ChatGPT, Claude and Gemini.
Topical guide - 5
Best AI Marketing Prompts
SEO, content, social, email, ads and brand — model-matched prompts for every channel.
Topical guide
Build prompts faster with Prompt InFlow
Browse 500+ tested prompts across every major AI model — or use our generators to build your own in seconds.