Start Here

ChatGPT Prompt Examples

A hand-picked set of the most useful ChatGPT prompts across work and study — each one copy-ready and shown with a real example output, so you can see what it does before you use it.

Most “ChatGPT prompt examples” lists are walls of one-line prompts with no proof they work. This page is different: every prompt below is a complete, reusable template with placeholders, and every one comes with an example of what ChatGPT actually returns. They span the jobs people use ChatGPT for most — writing emails, summarizing documents, drafting SEO content, prepping for interviews, and turning meetings into action items.

These are the highlights. When you find a category that fits your work, follow it to the full collection — there are dedicated pages of prompts for marketers, sales, teachers, students, recruiters and managers, plus model-specific sets for Gemini and Claude. Everything is free to copy with no account.

15 prompts · free to copy · example output on each

ChatGPTGeminiClaude

Cold outreach email to a new lead

Write a short, personalized cold email that earns a reply instead of a delete.

The prompt

You are an experienced B2B sales rep known for cold emails that get replies. Write a cold outreach email to [PROSPECT NAME], the [JOB TITLE] at [COMPANY].

Context:
- What we sell: [ONE-LINE PRODUCT DESCRIPTION]
- The problem we solve for companies like theirs: [PAIN POINT]
- One specific thing I noticed about their company: [TRIGGER / RESEARCH NOTE]

Rules:
- Under 120 words, plain language, no buzzwords.
- Open with the specific observation, not "I hope this finds you well."
- One clear call to action: a 15-minute call.
- Plain text, no markdown. Then give me 2 subject line options.

Example output

Subject A: a quick idea for [Company]'s new office Subject B: [Company] + faster ramp for new reps? Hi [Name], Saw [Company] just opened a second support office — congrats. Scaling support usually means new hires fielding the same 20 questions for weeks. We give support teams an answer layer trained on your own docs, so new reps ramp in days instead of months. [Similar company] cut their ramp time by about a third. Worth a 15-minute call next week to see if it'd fit your new office? Happy to work around your calendar. Thanks, [Your name]

TipPaste a real LinkedIn or news detail into the trigger line — generic openers are exactly what gets cold emails deleted. Asking for "2 subject line options" gives you something to A/B test.

ChatGPTGeminiClaude

Turn messy meeting notes into clear action items

Convert raw notes or a transcript into decisions, owners, and next steps.

The prompt

Below are raw notes from a team meeting. Turn them into a clean summary for people who weren't there.

Format:
1. **TL;DR** — 2 sentences.
2. **Decisions made** — bullet list.
3. **Action items** — a table: Task | Owner | Due date. If an owner or date wasn't stated, write "unassigned" — do not invent one.
4. **Open questions** — anything left unresolved.

Keep it factual. Don't add advice. Here are the notes:
[PASTE NOTES OR TRANSCRIPT]

Example output

**TL;DR** — The team approved the Q3 pricing test and pushed the mobile redesign to August. Two action items are unassigned. **Decisions made** - Run the pricing A/B test on the Pro plan starting July 1. - Delay the mobile redesign to August to avoid the holiday code freeze. **Action items** | Task | Owner | Due date | |---|---|---| | Set up pricing test in billing | Priya | Jun 27 | | Draft August launch timeline | unassigned | unassigned | | Tell support about the price change | Marco | Jun 30 | **Open questions** - Who signs off on the final August date?

TipThe "do not invent owners or dates" rule is what makes this trustworthy — AI otherwise fills gaps with plausible-but-wrong names. Paste a Zoom/Meet transcript directly for best results.

ChatGPTGeminiClaude

Summarize a research paper

Get the key claims, method, and findings of a dense paper.

The prompt

Act as a research methods tutor. I will give you the abstract and any sections I paste from a research paper. Summarize it using this structure:
1. Research question (one sentence)
2. Method (what they did, how many participants or data points)
3. Key findings (bullets, with numbers if they appear)
4. Limitations the authors mention
5. One sentence on why this paper matters

Do not interpret or add analysis. Use plain language I can explain to a classmate.

Paper excerpt: [PASTE ABSTRACT + KEY SECTIONS]

Example output

1. Research question: Does spaced repetition improve long-term retention compared to massed practice in undergraduate vocabulary learning? 2. Method: Randomized experiment, 94 undergraduate psychology students over 8 weeks; one group used a spaced flashcard app, one group did blocked study sessions. 3. Key findings: - Spaced group retained 31% more words at the 4-week follow-up test. - No significant difference at the immediate post-test (p = .42). - Effect was strongest for low-frequency words. 4. Limitations: Self-selected study time; both groups used the same word list. 5. Why it matters: Confirms spacing benefit persists beyond the lab and applies to a practical student tool.

TipIf the paper is long, paste the abstract and the Results section first. Those two alone give you 80% of the structure; add the Discussion only if you need the "why it matters" layer.

ChatGPTGeminiClaude

Interview questions tailored to a role

Generate skill- and behavior-based questions for a specific job.

The prompt

Create an interview question set for a [JOB TITLE] role at [COMPANY TYPE].

The role requires: [TOP 3–4 SKILLS OR RESPONSIBILITIES].

Give me:
- 3 technical or skill-based questions (test actual competence, not trivia).
- 4 behavioral questions using a real situation the candidate would have faced.
- 2 questions that reveal how they think about [SPECIFIC CHALLENGE THIS ROLE FACES].
- Under each question, add one line: what a strong answer includes.

Don't invent requirements I haven't given you.

Example output

Technical 1. "Walk me through how you've structured a sourcing funnel for a role with under 200 qualified candidates in the market." → Strong answer: a specific example with search strategy, outreach rate, and how they adapted. Behavioral 2. "Tell me about a time a hiring manager wanted a candidate you thought was wrong for the role. What did you do?" → Strong answer: held a position with data, didn't just defer. Thinking questions 3. "This role has a two-week time-to-fill target. What breaks first and how do you manage it?" → Strong answer: surfaces pipeline risk, sets expectations early, doesn't promise what they can't control.

TipAsk for "what a strong answer includes" in the same request — it forces the model to think about what you are actually trying to learn, not just generate questions that sound good.

ChatGPTGeminiClaude

Turn a reading into quiz questions

Generate comprehension questions at mixed difficulty from any text.

The prompt

You are an experienced curriculum designer. Generate a [NUMBER] question reading comprehension quiz based on the text below.

Grade level: [GRADE LEVEL]
Mix of difficulty:
- [NUMBER] recall questions (directly stated in the text)
- [NUMBER] inference questions (require reading between the lines)
- [NUMBER] synthesis or opinion question (requires connecting the text to a broader idea)

Format each question as:
Q[N]: [Question]
Type: Recall / Inference / Synthesis
Sample answer: [One correct answer in 1–2 sentences]

Text: [PASTE TEXT]

Example output

Q1: What two crops did the Dust Bowl destroy most severely in Oklahoma between 1934 and 1936? Type: Recall Sample answer: Wheat and cotton were the two crops most severely destroyed during the Dust Bowl years described in the passage. Q2: Why did many families leave even when they owned their land outright? Type: Inference Sample answer: Even landowners left because dust storms made farming impossible for years at a stretch, meaning owning the land didn't protect them from losing their income and food supply. Q3: The author argues that the Dust Bowl was partly caused by farming practices. Do you think knowing that changes how we should respond to today's droughts? Explain using the text. Type: Synthesis Sample answer: Varies — accept any response that connects the passage's evidence about over-plowing to a current policy or personal action.

TipSpecifying "sample answer" in the format prompt forces the model to verify each question is actually answerable from the text — a quick way to catch questions that are ambiguous or unanswerable.

ChatGPTGeminiClaude

Follow-up email after no reply

Nudge a silent prospect without sounding needy or repeating yourself.

The prompt

Write a follow-up email to a prospect who didn't reply to my first message [NUMBER] days ago.

Original email was about: [TOPIC / OFFER].

Rules:
- Don't say "just following up" or "bumping this."
- Add one new piece of value (a stat, a relevant example, or a resource) so the email stands on its own.
- Keep it under 80 words.
- End with a low-friction question they can answer in one line.

Example output

Subject: re: cutting your support ramp time Hi [Name], One more reason this might be worth a look: [Similar company] had the same "new reps drowning for weeks" problem and got first-week resolution rates up 22% after switching. If ramp time isn't a priority right now, no worries — just reply "not now" and I'll close the loop. Otherwise, open to 15 minutes Thursday? [Your name]

TipGiving them an easy "not now" out actually raises reply rates — people answer when saying no is painless. Swap the value line each follow-up so you never just repeat the pitch.

ChatGPTGeminiClaude

Write a weekly status report for your boss

Turn the week's work into a tight update leadership actually reads.

The prompt

You are a senior manager writing a weekly status report. Turn my bullet-point notes into a clean update my director will read in under two minutes.

Format:
1. **This week** — 3–5 bullets of concrete progress (metrics or deliverables, not effort).
2. **Next week** — 2–3 priorities with owners.
3. **Blockers** — anything I need from leadership. If none, write "None."

Rules: plain language, no filler phrases like "we continued to work on," numbers wherever I have them, under 200 words total.

My notes: [PASTE YOUR WEEK'S NOTES]

Example output

**This week** - Shipped the onboarding email sequence; open rate at 41% vs. 29% baseline. - Closed two enterprise pilots — Meridian Health and Solis Finance (combined ARR: $84,000). - Reduced P1 ticket backlog from 34 to 11 by reallocating two engineers from the feature queue. - Completed Q3 headcount plan; submitted to HR on Thursday. **Next week** - Priya: finalize security review for Meridian (due Thu). - Tom: start sprint 14 with new backlog priority order. - Me: present Q3 plan to leadership on Wednesday. **Blockers** - Need sign-off on the contractor extension for Tom's team by Monday — delays sprint 14 otherwise.

TipForce yourself to write numbers into the notes before pasting — "shipped onboarding emails" is useless; "open rate 41% vs. 29% baseline" is what leadership remembers. The AI can't invent metrics you didn't give it.

ChatGPTGeminiClaude

Write meta titles and descriptions

Generate click-worthy, length-safe SERP snippets.

The prompt

Write 3 meta title options and 2 meta description options for a page targeting [TARGET KEYWORD].

Page topic: [BRIEF DESCRIPTION OF PAGE CONTENT]
Audience: [WHO IS SEARCHING]

Rules:
- Titles: 50–60 characters including the keyword. No clickbait. Make each title take a different angle (keyword-first / benefit-first / question).
- Descriptions: 140–155 characters. Include the keyword, a clear benefit, and a soft call to action. No truncation.
- Label each option with its character count.

Example output

Titles: A: "Project Management Software for Agencies | [Brand]" — 51 chars | keyword-first B: "Run Client Projects Without the Chaos — [Brand]" — 48 chars | benefit-first C: "Which PM Tool Fits Your Agency? Compare Top 6" — 46 chars | question/comparison Descriptions: A: "Compare the top project management tools built for agencies. Retainer billing, client portals, and resource tracking in one place. See which fits your team." — 155 chars B: "Agency teams waste hours switching between tools. Find the PM software that handles clients, timelines, and billing — without the spreadsheet chaos." — 147 chars

TipGenerating titles in three distinct angles (keyword-first, benefit-first, question) gives you real creative range to A/B test, rather than minor word-order variations that perform the same.

ChatGPTGeminiClaude

Run a mock interview with AI

Practice a real interview with follow-ups and feedback.

The prompt

You are a recruiting coordinator at [COMPANY TYPE] interviewing me for a [ROLE] internship. Run a realistic mock interview with these rules:
- Ask one question at a time and wait for my answer before continuing.
- After I answer, give me a 2-sentence coaching note (what landed, what to tighten).
- Include at least one follow-up question per answer ("Can you be more specific about…").
- After 5 questions, give me an overall debrief: strengths, one pattern to fix, and one phrase I overused.

Start with: "Thanks for coming in — can you tell me a little about yourself?"

Example output

"Thanks for coming in — can you tell me a little about yourself?" [Student answers] Coaching note: Your opening was clear and included a relevant project — good. The second half drifted into listing coursework without connecting it to the role. End with one sentence on why this specific internship, not internships in general. Follow-up: "You mentioned the data project — what was your actual contribution versus the team's?" [Continues for 5 rounds] Overall debrief: Strong on specific examples. Pattern to fix: you front-load the context and rush the result — flip the ratio. Phrase you overused: "basically" (4 times). Replace it with a pause.

TipSet the company type to the actual company you are targeting, not a generic placeholder — the follow-up questions get sharper when the role context is real.

ChatGPTGeminiClaude

LinkedIn post from a customer win

Turn a customer result into a story-style post that builds pipeline, not bragging.

The prompt

Write a LinkedIn post based on a customer win. Use a story arc: the problem they had, the turning point, the result.

Details:
- Customer type: [INDUSTRY / SIZE, keep anonymous if needed]
- Before state: [PROBLEM + ROUGH NUMBER]
- After state: [RESULT + NUMBER]

Rules:
- First line must stop the scroll (no "Excited to share...").
- Conversational, short paragraphs, one takeaway lesson.
- Soft CTA at the end, not "DM me to buy."

Example output

A support team told me their new hires were "useless for a month." Their words, not mine. The problem wasn't the people. New reps were hunting through 400 pages of docs that changed every week — so they guessed, or pinged a senior rep, who then stopped doing their own job. We gave them one answer layer trained on those same docs. First-week resolution rates went from 51% to 73%. The lesson: onboarding speed is usually a findability problem, not a training problem. Curious how other support leaders are tackling ramp time — what's worked for you?

TipLead with a real quote or a number, never "Excited to share." End by asking a question so the post earns comments — which is what gets it shown to more feeds.

ChatGPTGeminiClaude

Summarize options into a decision memo

Lay out choices, trade-offs, and a recommendation for a fast decision.

The prompt

Write a decision memo for [DECISION MAKER / AUDIENCE] on the question: [THE DECISION TO BE MADE].

Format:
1. **Context** — why this decision is needed now (2–3 sentences).
2. **Options** — a table: Option | Pros | Cons | Cost/Effort.
3. **Recommendation** — which option you recommend and the one-sentence reason.
4. **What we need from you** — the specific ask (approval, a call, a sign-off).

Be direct. State a recommendation even if the data is imperfect. Under 300 words.

Details: [PASTE OPTIONS, TRADE-OFFS, YOUR PREFERRED CHOICE AND WHY]

Example output

**Decision: Hire vs. Contract for Design Role** To: [Director] | Date: Jun 17 **Context** The onboarding project needs a designer by July 1 to hit the Aug 31 ship date. The role has been open for six weeks; the pipeline has two candidates but no offer-ready finalist. **Options** | Option | Pros | Cons | Cost | |---|---|---|---| | Extend contractor (Lena) | Available now, knows the product | 20% premium, not a long-term fix | $12,000 for 8 weeks | | Wait for hire | Right long-term | Delays project 3–6 weeks | $0 now, risk of Q3 miss | | Freelancer via agency | Fast, low overhead | Ramp time, no product context | $8,000–$14,000 | **Recommendation** Extend Lena's contract through August. She's already ramped, and missing the August date costs more than the premium. **What we need from you** Approval to extend Lena at the current rate through Aug 31. I need this by Monday to give her enough notice.

TipState your recommendation explicitly — "option B" is not a recommendation. Saying "I recommend X because Y" forces you to commit, and it's exactly what decision-makers need to move fast. A memo that hedges everything is a memo that gets no action.

ChatGPTGeminiClaude

Screen a resume against a job spec

Summarize how a resume matches a role, with gaps flagged honestly.

The prompt

Screen the resume below against the job spec and give me a structured summary.

Job spec: [PASTE JOB SPEC]
Resume: [PASTE RESUME]

Format:
- Overall fit: Strong / Possible / Weak (one line of reasoning)
- Matches: bullets of where they meet the spec directly
- Gaps: bullets of missing requirements — be honest, don't soften
- One question worth asking them on a call

Don't invent qualifications. If something is ambiguous, say so rather than guessing.

Example output

Overall fit: Possible — strong on the technical side, light on the team leadership the spec asks for. Matches: - 6 years in data engineering, all in fintech (spec asks 4+). - Hands-on with dbt and Snowflake, which the spec names explicitly. - Led a pipeline migration project end-to-end. Gaps: - No evidence of managing other engineers — spec requires leading a team of 3+. - No mention of vendor negotiation or tooling budget ownership. - ML pipeline experience listed but no specifics; could be shallow. Question to ask: "The role manages two junior engineers from day one — have you had direct reports before, and what did that look like?"

TipAdd "if something is ambiguous, say so" to keep the model from reading gaps charitably. A resume screen that papers over missing requirements wastes everyone's time.

ChatGPTGeminiClaude

Write a LinkedIn thought-leadership post

Turn a point of view into a post that builds authority.

The prompt

Write a LinkedIn thought-leadership post for [MY NAME / PERSONA], who is a [ROLE] in [INDUSTRY].

My point of view: [STATE THE CONTRARIAN CLAIM OR OBSERVATION IN 1–2 SENTENCES]
Evidence or experience I can cite: [STAT, STORY, OR SPECIFIC EXAMPLE]
Who I am speaking to: [TARGET READER]

Rules:
- First line must be a hook that stops the scroll — no "I'm excited to share" or "Hot take:"
- Use short paragraphs (1–3 lines each)
- Share the real point of view, not a safe hedge
- End with a question that invites comments from the target reader
- 150–250 words

Example output

Most marketing teams are measuring the wrong thing after a content refresh. They track rankings. They should track revenue-per-visit. Here's why: we refreshed 14 old blog posts for a SaaS client last quarter. Average ranking improved by 6 positions. Organic traffic went up 31%. Conversions went down 4%. The posts that gained traffic were attracting earlier-stage readers who weren't ready to buy. Better rankings, worse business results. Once we filtered the keyword list to commercial-intent queries only and rewrote the CTAs to match where the reader was in the funnel — conversions recovered and then grew 18% over baseline. The lesson: "more traffic" is a vanity goal. "More traffic from people who buy" is a strategy. If you run content for a product-led company, what's the one metric you'd never give up in a board report?

TipNaming a specific result with a specific number (31% traffic increase, 4% conversion drop) does more for credibility than any general claim about expertise — specificity is what makes thought-leadership posts get saved and shared.

Keep browsing

Gemini prompts Claude prompts ChatGPT for work ChatGPT tips

Frequently asked questions

What is a good ChatGPT prompt?

A good prompt gives ChatGPT a role, clear context, constraints (length, tone, format), and a guardrail against making things up. The examples here follow that pattern — that’s why their output is usable instead of generic. Just replace the bracketed placeholders with your own details.

How do I use these prompt examples?

Click Copy on any prompt, paste it into ChatGPT (or Gemini or Claude), and replace the [BRACKETED] placeholders with your specifics. The example output under each prompt shows the kind of result to expect.

Do these prompts work in Gemini and Claude too?

Yes. The prompts on this page are model-agnostic and work in all three. We also have prompt sets written specifically for Gemini (Google Workspace, research) and Claude (long documents, careful writing).

Are the example outputs real?

They’re realistic, representative samples of what each prompt produces — not live API calls. Exact wording varies by model and version, but the structure and quality are what you can expect.

ChatGPT Prompt Examples

Cold outreach email to a new lead

Write an SEO content brief

Turn messy meeting notes into clear action items

Summarize a research paper

Interview questions tailored to a role

Repurpose a blog post into social

Turn a reading into quiz questions

Follow-up email after no reply

Write a weekly status report for your boss

Write meta titles and descriptions

Run a mock interview with AI

LinkedIn post from a customer win

Summarize options into a decision memo

Screen a resume against a job spec

Write a LinkedIn thought-leadership post

Keep browsing

Frequently asked questions