Author: admin

  • 12 AI Study Prompts for Students That Help You Learn (Not Cheat)

    AI can make you a much better student, or it can make you a worse one. If it writes your essays and solves your problem sets, you skip the learning and risk breaking your school’s academic integrity policy. If you use it as a tutor that explains, quizzes and gives feedback, it can be one of the most effective study tools ever built. These 12 prompts are designed for the second approach: they help you understand material, remember it, and improve your own work.

    Check your class syllabus and school policy on AI use. Policies differ between courses, and some instructors allow AI for brainstorming or feedback but not for writing. When in doubt, ask your instructor.

    Understand difficult topics

    1. Explain it at my level

    You are a patient tutor. Explain [Topic] to me. I am a [Grade or Level, e.g. high school junior / first-year college] student.
    What I already understand: [What You Know]
    What confuses me: [What Confuses You]
    
    1. Explain it in plain language using one everyday analogy
    2. Walk through one example step by step
    3. Ask me 2 questions to check that I understood, and wait for my answers

    Why it works: Telling the AI what you already know and what confuses you targets the explanation at the exact gap, instead of repeating what is in your textbook.

    2. The Feynman technique

    I will explain [Topic] in my own words as if teaching a 12-year-old. Then point out: anything I got wrong, anything important I left out, and any place where I used jargon to hide that I do not fully understand. Do not rewrite my explanation; ask me questions that help me fix it myself.
    My explanation: [Your Explanation]

    3. Concept map

    Create a text-based concept map of [Unit or Chapter Topic] showing the main ideas, how they connect, and one example for each. Then tell me which 3 connections students most often misunderstand.

    Study and memorize

    4. Quiz me one question at a time

    Quiz me on [Topic] using these notes: [Paste Notes]
    Ask one question at a time and wait for my answer. Mix multiple choice, short answer and one "explain why" question. After each answer, tell me if I am right, explain briefly, and adjust the difficulty based on how I am doing. After 10 questions, summarize my weak spots.

    Retrieval practice, actively recalling information, is one of the best-supported study techniques in learning research. This prompt turns any notes into retrieval practice.

    5. Make flashcards

    Turn these notes into 20 flashcards in the format "Front | Back". Keep each card to one fact or concept. Include 5 cards that ask "why" or "how", not just definitions.
    [Paste Notes]

    6. Build a study schedule

    My exam on [Subject] is on [Date]. Topics covered: [Topics]. My weakest areas: [Weak Areas]. I can study [Hours] hours on weekdays and [Hours] on weekends.
    Create a day-by-day study plan using spaced repetition and practice testing, with more time on weak areas and a review day before the exam. Include short breaks.

    7. Practice exam

    Write a practice exam for [Course] covering [Topics], similar in style to this sample question from my class: [Sample Question]. 10 questions, increasing in difficulty. Do not show the answers until I submit all of mine, then grade me and explain each mistake.

    Writing (the right way)

    8. Brainstorm thesis options

    I am writing a [Length] essay for [Class] on [Prompt or Topic]. Help me brainstorm: suggest 5 possible thesis directions, the strongest argument and counterargument for each, and the kind of evidence I would need. Do not write the essay.

    9. Feedback on my draft

    Act as a demanding but encouraging writing instructor. Give feedback on my draft below using this rubric: [Paste Rubric or "thesis, evidence, organization, clarity, grammar"].
    For each criterion, give a score out of 5, quote one place that shows the problem, and explain how I could fix it. Do not rewrite my essay for me.
    [Paste Draft]
    Weak prompt result
    “Write me a 1,000-word essay on the causes of World War I.” (Produces an essay you did not write, cannot defend in class, and that may violate your school’s policy.)
    Engineered prompt result
    Rubric-based feedback showing your thesis is a summary rather than an argument, that paragraph 3 lacks evidence, and that your conclusion introduces a new idea, with questions that help you fix each issue yourself.

    10. Outline check

    Here is my essay outline: [Paste Outline]
    Does each section support my thesis? Is anything out of order or missing? What would a skeptical reader object to? Answer in bullet points.

    Math and science

    11. Hint, not the answer

    I am stuck on this problem: [Paste Problem]
    Here is my work so far: [Your Work]
    Do not solve it. Tell me whether my approach is on the right track, point to the first step where I went wrong (if any), and give me a hint for the next step only.

    12. Check my reasoning

    I solved this problem: [Problem]. My answer and steps: [Your Steps]
    Check each step. If a step is wrong, explain the concept behind the mistake and give me a similar practice problem to try.

    Tips for studying with AI

    • Verify facts. AI can be wrong, especially with dates, quotes and citations. Check against your textbook and class materials.
    • Never submit fake citations. AI tools sometimes invent sources. Find and read every source yourself.
    • Do the work first. Attempt problems before asking for help, then use AI to check and explain.
    • Use voice mode. Explaining concepts out loud to an AI tutor is great practice for oral exams and presentations.

    Frequently asked questions

    Is using ChatGPT for homework cheating?

    It depends on how you use it and your instructor’s policy. Getting explanations, quizzes and feedback is generally treated differently from submitting AI-written work as your own. Always follow your course rules and disclose AI use when required.

    Can teachers detect AI writing?

    AI detectors are unreliable and can produce false positives, but instructors often notice writing that does not match a student’s usual voice or cannot be explained in conversation. The safest approach is to do your own writing and use AI for feedback.

    Which AI is best for studying?

    ChatGPT, Claude and Gemini all work well as tutors. Many offer dedicated study or learning modes that guide you with questions instead of giving answers directly, which pairs well with these prompts.

  • 10 ChatGPT Prompts for Budgeting and Personal Finance (Safely)

    AI assistants are surprisingly good at the tedious parts of personal finance: categorizing spending, building a budget template, explaining confusing terms, and comparing options side by side. They are not a replacement for a licensed financial professional, and they do not know your full situation. These 10 prompts are designed to help you organize information and understand your choices, so you can make better decisions yourself.

    Important: this content is educational and is not financial, tax or investment advice. Never paste account numbers, Social Security numbers, passwords or full statements into an AI tool. Replace names and numbers you consider sensitive with rounded figures or placeholders. Verify tax rules and contribution limits on IRS.gov, because they change every year.

    Budgeting

    1. Build a zero-based budget

    Act as a patient budgeting coach. Help me build a zero-based monthly budget.
    
    Monthly take-home pay: [Take-Home Pay]
    Fixed costs: [Rent or Mortgage, Utilities, Insurance, Loan Payments]
    Variable spending (rough estimates): [Groceries, Gas, Dining, Subscriptions, Other]
    Goals: [Emergency Fund, Pay Off Debt, Save for X]
    
    Create a table with categories, planned amounts and percentage of income. Every dollar should be assigned. Point out where my spending is high compared with common budgeting guidelines like 50/30/20, and suggest 3 realistic cuts. Ask me questions if something seems missing.

    Why it works: Rounded estimates are enough for a useful first budget, and you avoid sharing exact account data. The comparison with 50/30/20 gives you a reference point, not a rule.

    2. Categorize your spending

    Here is a list of my transactions from last month with merchant names and amounts only (no account numbers): [Paste Transactions]
    Categorize each into: Housing, Utilities, Groceries, Dining, Transportation, Subscriptions, Shopping, Health, Entertainment, Other. Give totals per category, flag subscriptions I might have forgotten, and list my top 5 merchants by spend.

    3. Find subscriptions to cancel

    Here are my recurring subscriptions and their monthly cost: [List]
    Rank them by cost per use based on how often I use each: [Usage Notes]. Suggest which to cancel, downgrade or rotate (for example, keeping only one streaming service at a time), and calculate my annual savings.

    Debt and savings

    4. Compare debt payoff strategies

    I have these debts: [For Each: Type, Balance, APR, Minimum Payment]
    I can pay [Extra Amount] extra per month.
    Compare the avalanche method (highest interest first) and the snowball method (smallest balance first): payoff order, approximate months to debt-free, and approximate total interest for each. Show your math assumptions. Explain the trade-off between saving money and staying motivated.

    AI arithmetic over many months can contain errors. Use the results to understand the strategies, then confirm with a dedicated debt payoff calculator or spreadsheet.

    5. Emergency fund plan

    My essential monthly expenses are [Amount]. I currently have [Savings] saved. I can save [Monthly Amount] per month.
    Explain how big an emergency fund people commonly aim for and why, calculate how long I will take to reach 3 and 6 months of expenses, and suggest where people typically keep emergency funds (for example, high-yield savings accounts) and what to compare when choosing one.

    6. Savings goal planner

    I want to save [Goal Amount] for [Goal] by [Date]. I have [Current Savings].
    Calculate the monthly amount needed, show a month-by-month table, and suggest 3 ways to reach it faster based on my budget: [Budget Summary].

    Understanding money topics

    7. Explain a financial term simply

    Explain [Term, e.g. Roth IRA vs traditional IRA / APR vs APY / credit utilization] in plain English for someone new to personal finance in the US.
    Use one everyday example with simple numbers. List the most common misunderstanding about it. Tell me which official source I should check for current rules or limits.

    8. Compare two financial products

    Compare these two [Product Type, e.g. credit cards / savings accounts] in a table using only the details I paste from their official pages:
    Option A: [Details]
    Option B: [Details]
    My usage: [How I Would Use It]
    Calculate the approximate yearly value or cost of each for my usage. List questions I should ask before choosing. Do not recommend a specific product; help me compare.

    9. Prepare questions for a financial professional

    I am meeting a [Financial Advisor / CPA / Mortgage Lender] about [Topic]. My situation in general terms: [Summary].
    Write 10 smart questions to ask, including questions about fees, how they are paid, whether they act as a fiduciary, and what documents I should bring.

    10. Understand a bill or statement

    Explain the sections of this [Bill Type, e.g. medical bill / credit card statement / pay stub] in plain English. I have removed personal details: [Paste Redacted Text]
    Flag any charges or deductions that look unusual and tell me what questions to ask the provider or my employer.
    Weak prompt result
    “How do I save money?” returns a generic list: make coffee at home, use coupons, spend less.
    Engineered prompt result
    A budget table built from your real categories that shows dining out at 14% of take-home pay, three specific cuts worth about $340 a month, and a timeline to a 3-month emergency fund.

    Using AI safely with money

    • Redact first. Remove names, account numbers and addresses before pasting anything.
    • Check the math. Ask the AI to show its calculations, and confirm important numbers in a spreadsheet or calculator.
    • Check the date. Tax brackets, contribution limits and interest rates change. Confirm on official sources such as IRS.gov.
    • Watch for scams. No legitimate AI tool will ask for your bank login. Be wary of “AI trading bots” promising guaranteed returns.

    Frequently asked questions

    Can ChatGPT give me investment advice?

    AI tools can explain concepts and help you organize questions, but they are not licensed advisors, do not know your full situation, and may be out of date. For personalized advice, consult a qualified fiduciary financial professional.

    Is it safe to upload my bank statement to AI?

    We do not recommend uploading full statements. Copy only the merchant names and amounts you need, and check your AI tool’s privacy and data-training settings.

    Which AI is best for budgeting?

    Any major assistant can help. Tools that can run code or create spreadsheets are helpful for calculations, since they compute rather than estimate.

  • 12 Midjourney Product Photography Prompts for Etsy, Shopify and Amazon Sellers

    Professional product photos are one of the biggest costs for Etsy sellers, Shopify brands and Amazon sellers. AI image generators like Midjourney can produce lifestyle scenes, styled flat lays and ad creatives in minutes. This playbook gives you 12 product photography prompts, explains how each part of an image prompt works, and shows how to adapt them for your own products.

    Honesty matters: marketplaces and US consumer protection rules expect product images to represent what customers actually receive. Use AI scenes for lifestyle, backgrounds and ad concepts, and make sure your main listing photos accurately show the real product. Many sellers combine a real product photo with an AI-generated background using image editing tools.

    How an image prompt is built

    Image models respond to descriptions, not instructions. Instead of “please make a nice photo”, describe the finished picture in this order:

    1. Subject: the product, described precisely (material, color, size, shape).
    2. Setting: surface and background.
    3. Style: the type of photography or art.
    4. Lighting: often the biggest factor in whether an image looks professional.
    5. Camera and composition: lens, angle, depth of field.
    6. Parameters: Midjourney settings at the end, such as --ar for aspect ratio and --no to exclude things.

    Our Prompt Enhancer has an image mode that builds prompts in this order for you. Midjourney adds and changes features with new model versions, so check its documentation for the latest parameters.

    Clean e-commerce shots

    1. White background hero shot

    [Product, e.g. matte black stainless steel water bottle, 24 oz], centered on a seamless pure white background, soft even studio lighting with a subtle shadow beneath, commercial e-commerce product photography, 100mm macro lens, ultra sharp detail, true-to-life color --ar 1:1 --no text, logo, props

    2. Floating product with soft shadow

    [Product] floating slightly above a pale [Color] surface, soft diffused overhead light, gentle contact shadow, minimalist premium advertising style, clean negative space on the right for text --ar 4:5

    3. Ingredient or component flat lay

    top-down flat lay of [Product] surrounded by its key ingredients [Ingredients], arranged neatly on a [Surface, e.g. light oak board], soft natural window light, editorial food and beauty photography, balanced composition --ar 4:5

    Works well for skincare, candles, coffee, snacks and supplements. Only show ingredients the product actually contains.

    Lifestyle scenes

    4. In-use lifestyle shot

    [Product] being used on a [Setting, e.g. sunny apartment balcony] by a person whose face is out of frame, natural candid moment, golden hour sunlight, lifestyle photography for a US direct-to-consumer brand, 35mm lens, shallow depth of field, warm tones --ar 4:5

    Keeping faces out of frame avoids uncanny results and keeps attention on the product.

    5. Seasonal holiday scene

    [Product] on a rustic wooden table with cozy winter holiday decor, pine branches, warm string lights softly blurred in the background, evening ambient light, festive gift-guide product photography --ar 2:3

    6. Desk and workspace setup

    [Product] on a modern minimalist home office desk next to a laptop and a ceramic mug, morning window light, neutral beige and white palette, tech lifestyle photography, 50mm lens --ar 16:9 --no text, screen glare

    7. Outdoor adventure scene

    [Product] resting on a granite rock beside a mountain trail, dramatic early morning light, mist in the valley behind, outdoor gear catalog photography, crisp detail on the product, background softly blurred --ar 3:2
    Weak prompt result
    “water bottle photo nice background” produces a random bottle that does not resemble the real product, in an unrelated scene, with odd lighting.
    Engineered prompt result
    A matte black bottle with the correct shape and size cues on a granite rock, dramatic morning light, misty valley, sharp product detail and soft background, at a 3:2 ratio ready for a banner.

    Ads and social media

    8. Pinterest pin background

    [Product] on a soft [Color] linen background with dried flowers, airy bright light, Pinterest aesthetic, lots of empty space at the top for a headline --ar 2:3

    9. Bold ad creative

    [Product] on a solid vivid [Brand Color] background with a single hard spotlight creating a long dramatic shadow, bold modern advertising style, high contrast, centered composition --ar 1:1

    10. Instagram Story vertical

    close-up of hands holding [Product] in a bright cafe, natural light, candid social media style, shallow depth of field, room at top and bottom for text --ar 9:16

    Brand and packaging

    11. Packaging concept

    premium packaging concept for [Product Type], [Material, e.g. recycled kraft paper box with embossed details], [Brand Style] design language, studio product shot on a neutral background, soft lighting --ar 4:5 --no readable text

    AI image models often garble text. Exclude text in the prompt and add your logo and copy afterwards in a design tool.

    12. Consistent brand collection

    [Product], [Surface], [Background], [Lighting], [Color Palette] color palette, consistent brand photography series, [Style] --ar 4:5

    Lock the surface, background, lighting and palette, and change only the product. That gives your shop a consistent look. Fill this one in with the Midjourney template.

    Troubleshooting common problems

    • Product looks wrong: describe it more precisely (material, finish, proportions) and use an image reference of your real product if your tool supports it.
    • Image looks fake or plastic: name a specific lighting setup and lens, and use photography terms rather than “realistic”.
    • Too busy: remove props and add “minimalist” and “negative space”.
    • Wrong crop: set the aspect ratio for the platform: 1:1 marketplace, 4:5 Instagram feed, 2:3 Pinterest, 9:16 Stories, 16:9 banners.

    Frequently asked questions

    Can I sell products using AI-generated photos?

    You can use AI images in marketing, but your listing images must not mislead customers about what they will receive. Check the image rules of your marketplace, such as Etsy or Amazon, and the terms of your image generator for commercial use.

    Do these prompts work in other image generators?

    Yes. The descriptive part works in most tools. Parameters like –ar and –no are Midjourney-specific; in other tools, set aspect ratio in the settings and write “without text” in the description.

    Who owns AI-generated images?

    Copyright protection for purely AI-generated images is limited under current US Copyright Office guidance, and each tool has its own terms. Read your generator’s terms and consider adding your own creative edits.

  • How to Write Better AI Prompts: A Practical Guide for ChatGPT, Claude and Gemini

    You do not need to be technical to write great prompts. You need to give an AI the same information you would give a smart new colleague on their first day: what the job is, who it is for, what good looks like, and what to avoid. This guide explains the techniques that consistently improve results across ChatGPT, Claude and Gemini, with examples you can copy and adapt.

    The anatomy of a great prompt

    Nearly every high-quality prompt has the same six ingredients. You will not always need all six, but checking for them is the fastest way to fix a disappointing answer.

    1. Role: who the AI should act as. “A CPA who works with freelancers” gives different answers than “an assistant”.
    2. Task: the specific thing to produce, stated with a strong verb: write, compare, summarize, critique, plan.
    3. Context: facts the AI cannot guess, such as your product, your audience, your past attempts and your constraints.
    4. Requirements: tone, length, format and rules such as “no jargon” or “under 150 words”.
    5. Examples: a sample of what you want, or of your own style. This is often the single most powerful addition.
    6. Output format: exactly how to present the answer, such as a table, bullet list, JSON or email with subject line.

    The Prompt Enhancer walks you through these ingredients and assembles the prompt for you.

    Before and after

    Weak: Write a blog post about remote work.
    Strong:
    You are an HR consultant who advises US companies with 20-200 employees.
    
    Write a 900-word blog post for small-business owners who are deciding whether to bring remote employees back to the office.
    
    Context: our readers are practical and skeptical of trends. Many have tried hybrid schedules with mixed results.
    
    Requirements:
    - Balanced: cover real advantages and drawbacks of each option
    - Include one short, realistic example of a 50-person company
    - Plain English, no buzzwords
    - H2 subheadings, and end with a 5-question checklist owners can use to decide
    
    Do not cite specific statistics unless you are confident they are accurate; if you mention research, describe it generally.

    The second prompt is longer, but every line adds information or removes a likely problem. That is the test of a good prompt: not length, but density of useful instruction.

    Seven techniques that work in every major model

    1. Show an example (few-shot prompting)

    If you want a specific style or format, show it. Two or three examples teach the AI more than a paragraph of description.

    Write 5 product taglines in this style:
    - "Coffee that keeps up with you."
    - "Shoes for the long way home."
    Product: a reusable water bottle that keeps drinks cold for 24 hours.

    2. Ask for reasoning before the answer

    For analysis, math, planning or decisions, ask the model to work through the problem before concluding. Many current models do this automatically, but asking explicitly still helps on complex tasks, and lets you check the logic.

    Before recommending an option, list the key factors, evaluate each option against them, and then give your recommendation with the single biggest risk.

    3. Let the AI ask questions first

    Before you start, ask me up to 5 questions about anything you need to know to do this well. Wait for my answers.

    This is ideal for complex tasks like business plans, where you might not realize what information is missing.

    4. Use delimiters for pasted material

    When you paste documents, separate them clearly from your instructions. Claude responds especially well to XML-style tags; ChatGPT and Gemini work well with tags or Markdown headings.

    Summarize the contract below in plain English and list any unusual clauses.
    
    <contract>
    [Paste Contract]
    </contract>

    5. Say what to do, not only what to avoid

    “Do not be wordy” is weaker than “Use short sentences and keep it under 120 words.” Positive instructions give the model a target.

    6. Break big tasks into steps

    Instead of asking for a complete marketing plan in one prompt, ask for a customer analysis first, then positioning, then the channel plan. Review each step before moving on. This is called prompt chaining, and it produces much better long work.

    7. Ask for a self-review

    After writing your draft, review it against my requirements, list anything missing or weak, and then give me only the improved final version.

    Model-specific tips

    • ChatGPT (OpenAI): responds well to Markdown structure and clear headings. Use Custom Instructions or Projects to save context you repeat often.
    • Claude (Anthropic): excellent with long documents and detailed instructions. XML tags help it keep sections separate. Projects let you store reference files.
    • Gemini (Google): integrates with Google search and Workspace. Ask it to flag information that may be out of date, and verify facts it pulls from the web.
    • Image models such as Midjourney: use descriptive phrases, not instructions: subject, style, lighting, composition, then parameters like –ar. See our product photography prompts.

    Common mistakes

    • Too little context. The AI fills gaps with generic assumptions. Add specifics.
    • Several tasks in one prompt. Split them.
    • Accepting the first answer. Reply with specific feedback: “Make the second paragraph more concrete and cut the last one.”
    • Trusting facts blindly. AI can state wrong information confidently. Verify numbers, quotes, laws and citations.
    • Pasting sensitive data. Remove personal, financial and confidential information first.

    Turn good prompts into templates

    When a prompt works, save it with the changing parts in square brackets, like [Audience] and [Topic]. Paste it into our Prompt Template Builder to get a reusable fill-in form.

    Frequently asked questions

    Is prompt engineering still useful as models get smarter?

    Yes. Smarter models need fewer tricks, but they still cannot read your mind. Context, examples and clear requirements will always matter because they carry information only you have.

    How long should a prompt be?

    As long as it needs to be to include the necessary information, and no longer. A quick question needs one sentence. A brand-specific marketing email might need 200 words of context.

    Do magic phrases like “take a deep breath” work?

    Effects from phrases like this were small and inconsistent even in older models. Clear context and requirements make a far bigger difference.

  • 12 AI Coding Prompts for Developers: Debugging, Code Review and Tests

    AI coding assistants are now part of most developers’ daily workflow, but the quality of the help depends heavily on how you ask. “Fix this” with a pasted stack trace gets you a guess. A prompt with context, constraints and a clear output format gets you a reviewed, tested answer. These 12 prompts cover the tasks developers use AI for most: debugging, code review, refactoring, tests, documentation and learning a new codebase.

    Security first: do not paste secrets, API keys, credentials, customer data or proprietary code your employer has not approved for AI tools. Check your company’s AI policy and your tool’s data-retention settings.

    Debugging

    1. Structured bug report for the AI

    You are a senior [Language/Framework] engineer helping me debug.
    
    Expected behavior: [What Should Happen]
    Actual behavior: [What Happens]
    Error message and stack trace:
    [Paste Error]
    
    Relevant code:
    [Paste Code]
    
    Environment: [Versions, OS, runtime]
    What I already tried: [Attempts]
    
    First list the 3 most likely root causes ranked by probability with your reasoning. Then give the fix for the most likely cause, and tell me how to confirm it is the real cause before I apply it.

    Why it works: “What I already tried” stops the AI from repeating suggestions you ruled out. Asking for ranked hypotheses before the fix encourages reasoning instead of a confident guess.

    2. Rubber-duck debugging

    I am going to explain my code line by line. Do not fix anything yet. After each section, ask me one question about assumptions I might be making. When you spot the likely bug, tell me which line and why, and let me try to fix it first.
    [Paste Code]

    3. Explain an unfamiliar error

    Explain this error to me like a senior teammate would: what it means, the 3 most common causes, and how to find which one applies to me.
    [Paste Error]
    My stack: [Stack]

    Code review and refactoring

    4. Thorough code review

    Review this [Language] code as a strict senior engineer.
    Context: [What It Does, Where It Runs, Scale]
    
    [Paste Code]
    
    Check: correctness and edge cases, security (injection, auth, secrets, input validation), performance, error handling, readability and naming, and testability.
    Return a table: Severity (High/Medium/Low), Location, Issue, Suggested Fix. Then show the corrected code with comments only where you changed something.
    Weak prompt result
    “Looks good overall! Maybe add some comments and consider error handling.” (Vague praise, nothing actionable.)
    Engineered prompt result
    A table with a High-severity SQL injection risk in a string-built query, a Medium missing-null check on an API response, and a Low naming issue, followed by corrected code using parameterized queries.

    5. Refactor without changing behavior

    Refactor this code to improve readability and maintainability WITHOUT changing its external behavior or public interface.
    [Paste Code]
    Constraints: [Style Guide, Language Version, No New Dependencies]
    Explain each change in one line. List any behavior you were unsure about instead of guessing.

    6. Performance optimization

    This function is slow with [Data Size] inputs: [Paste Code]
    Analyze its time and space complexity, identify the bottleneck, and propose an optimized version. Show before and after complexity, and note any trade-offs in readability or memory.

    Tests and documentation

    7. Unit tests with edge cases

    Write unit tests for this function using [Test Framework]:
    [Paste Code]
    Cover: the happy path, boundary values, empty and null inputs, invalid types, and error conditions. Use descriptive test names. List any edge case you think the function currently handles incorrectly.

    8. README for a project

    Write a README.md for this project: [Project Description, Main Files, Setup Steps]
    Sections: what it does, quick start, configuration, usage examples, project structure, contributing, and license placeholder. Use clear Markdown and keep the quick start under 6 steps.

    9. Docstrings and comments

    Add docstrings in [Style, e.g. Google / JSDoc] to every public function in this code. Explain parameters, return values, raised errors and one usage example. Do not change any code. Remove comments that only restate what the code obviously does.
    [Paste Code]

    Learning and architecture

    10. Understand a new codebase

    I just joined a project. Here is the folder structure and key files: [Paste Tree and Key Files]
    Explain: what the app does, how a request flows through the system, where the main business logic lives, and which 5 files I should read first and why. Then give me 3 safe first tasks to learn the codebase.

    11. Compare approaches before you build

    I need to build [Feature] in [Stack]. Compare 3 implementation approaches in a table: complexity, performance, maintainability, cost, and when each is the right choice. Recommend one for my constraints: [Team Size, Scale, Deadline].

    12. Translate code between languages

    Convert this [Source Language] code to idiomatic [Target Language]:
    [Paste Code]
    Use the target language's standard conventions and libraries, not a line-by-line translation. Point out any behavior that differs between the languages, such as integer division, null handling or concurrency.

    Model notes for developers

    • Claude handles long files and multi-file context well. Wrapping each file in tags such as <file name=”api.py”> keeps large prompts organized.
    • ChatGPT works well with Markdown code fences and is fast for quick iterations.
    • Gemini has a very large context window, useful when you need to paste a lot of code at once.
    • Whichever you use, run the code and the tests. AI-generated code can look correct and still be wrong.

    Building AI into your own app? Estimate what these prompts would cost at scale with our AI Token and Cost Calculator.

    Frequently asked questions

    Is it safe to paste company code into ChatGPT or Claude?

    It depends on your employer’s policy and your plan. Business and enterprise plans usually offer stronger data protections than free consumer plans. When in doubt, ask, and never paste secrets.

    Why does the AI give me code that does not run?

    Usually missing context: library versions, the rest of the file, or the runtime environment. Include versions and the exact error. Ask the AI to list its assumptions.

    Should junior developers use AI?

    Yes, as a tutor rather than an autopilot. Prompt 2 and prompt 10 are designed to help you learn, not just get answers.

  • 14 AI Marketing Prompts for Small Businesses (Email, Ads, Social and SEO)

    A marketing agency retainer can cost a small business thousands of dollars a month. AI will not replace a great strategist, but it can do a large share of the day-to-day work: drafting emails, writing ad variations, planning content and analyzing customer feedback. The catch is that AI only knows what you tell it. These 14 prompts are built to pull out the details that make marketing work: your customer, your offer, and what makes you different.

    Start with prompt 1. It creates a “brand brief” you can paste into every other prompt, so the AI writes like your business every time.

    Foundation

    1. Create your reusable brand brief

    You are a brand strategist for US small businesses. Interview me to create a one-page brand brief.
    
    Ask me these questions one at a time, waiting for each answer:
    1. What do you sell, and what does it cost?
    2. Who is your best customer? Describe a real one.
    3. What problem do they have before they find you?
    4. Why do customers choose you over competitors?
    5. What do customers praise in reviews? (paste examples)
    6. What words describe your brand voice, and what should it never sound like?
    7. What is your main marketing goal for the next 90 days?
    
    Then write the brief with sections: Offer, Ideal Customer, Core Problem, Differentiators, Proof, Voice Guidelines, 90-Day Goal. Keep it under 400 words so I can paste it into future prompts.

    Why it works: Every later prompt gets better because it starts from your real positioning instead of generic assumptions. Save the brief somewhere you can copy it quickly.

    2. Customer persona from real reviews

    Here are real reviews and customer messages: [Paste Reviews]
    Identify: the top 5 reasons customers buy, the exact phrases they use to describe their problem, objections or hesitations mentioned, and 3 customer segments. Quote the reviews as evidence. Then suggest 5 marketing headlines that use the customers' own language.

    Email marketing

    3. Welcome email sequence

    [Paste Brand Brief]
    
    Write a 4-email welcome sequence for new subscribers who joined through [Lead Magnet or Signup Reason].
    Email 1 (immediately): deliver the promise, introduce us in 2 sentences
    Email 2 (day 2): the most useful tip for their core problem
    Email 3 (day 4): customer story and proof
    Email 4 (day 7): offer [Offer] with a clear deadline
    For each: subject line under 45 characters, preview text, body under 200 words, one call to action.

    4. Promotional email that does not sound desperate

    [Paste Brand Brief]
    Write a promotional email for [Promotion] running [Dates]. Lead with the customer benefit, not the discount. Include one line of social proof: [Proof]. Give 5 subject line options and mark the one you would test first and why.

    Advertising

    5. Google Ads responsive search ads

    You are a PPC specialist for local US businesses.
    Business: [Business Name], a [Business Type] in [City, State]
    Service: [Service]. Differentiator: [Differentiator]. Offer: [Offer]
    Write 15 headlines (max 30 characters) and 4 descriptions (max 90 characters). Include the city in 3 headlines and a number or price in 3. Show the character count after each line and fix any that are over.

    AI models sometimes miscount characters. Asking for the count makes errors easy to spot, but double-check in Google Ads before publishing.

    6. Facebook and Instagram ad angles

    [Paste Brand Brief]
    Give me 6 different ad angles for [Product or Service], each targeting a different motivation (save time, save money, status, fear of missing out, convenience, trust). For each angle: a hook (first line), primary text under 125 characters, a headline under 40 characters, and an image or video concept.
    Weak prompt result
    “Check out our amazing cleaning services! We are the best in town. Call now for a quote!” (No customer, no benefit, no proof, no reason to act.)
    Engineered prompt result
    “Back from work to a spotless home every Friday. 4.9 stars from 312 Austin families. First clean 20% off when you book by Sunday.” (Specific outcome, local proof, clear offer and deadline.)

    Content and social media

    7. 30-day content calendar

    [Paste Brand Brief]
    Create a 30-day social media calendar for [Platforms]. Mix: 40% helpful tips, 20% behind the scenes, 20% customer proof, 20% offers. For each day: content pillar, post idea, caption hook, and format (Reel, carousel, photo, story). Note any US holidays or seasonal moments in [Month] that fit my business.

    8. Repurpose one piece of content into ten

    Here is a blog post or video transcript: [Paste Content]
    Repurpose it into: 1 LinkedIn post, 3 tweets or Threads posts, 1 Instagram carousel (slide-by-slide text), 1 short video script under 45 seconds, 1 email newsletter section, and 3 quote graphics. Keep my voice: [Voice].

    9. Local SEO Google Business Profile posts

    Write 8 Google Business Profile posts for [Business Name] in [City, State]. Mix updates, offers and tips. Each under 150 words, naturally mention the city and service, and end with a call to action button suggestion (Call, Book, Learn more).

    Sales and customer experience

    10. Landing page copy

    [Paste Brand Brief]
    Write landing page copy for [Offer]. Sections: headline and subheadline, 3 benefit blocks, how it works in 3 steps, testimonials placeholder, FAQ with 5 real objections, final call to action. Make the headline specific and outcome-focused. Give 3 headline options.

    11. Respond to a negative review

    Write a public reply to this negative review: [Paste Review]
    Facts from our side: [Your Side]
    Rules: thank them, acknowledge the specific issue, no excuses or arguing, mention one concrete fix, invite them to contact [Contact Method] offline. Under 100 words. Calm and human.

    12. Pricing page and package names

    I offer these services and prices: [Services and Prices]. Suggest how to package them into 3 tiers (good, better, best), with names, what is included in each, who each is for, and which tier to highlight as most popular. Explain the reasoning using pricing psychology.

    Analysis and strategy

    13. Competitor positioning analysis

    Here is copy from three competitors' websites: [Paste Copy With Names]
    Analyze how each positions itself, what promises they make, what they ignore, and where there is a gap I can own. Then suggest 3 positioning statements for my business that are clearly different.

    14. Monthly marketing review

    Here are my marketing results for [Month]: [Paste Metrics: traffic, leads, sales, email open rates, ad spend, cost per lead]
    Explain what is working, what is not, and the 3 highest-impact changes to make next month. Be direct. If data is missing to make a conclusion, tell me what to track.

    Which AI model to use

    ChatGPT, Claude and Gemini all handle these prompts well. Claude is especially good at following a long brand brief consistently. ChatGPT is fast for generating many variations. Gemini is useful when you want help researching current trends, but verify anything it presents as a fact. If you plan to automate these prompts through an API, estimate costs first with our AI Token and Cost Calculator.

    Frequently asked questions

    Can AI really replace a marketing agency?

    For execution tasks such as drafting, ad variations and content calendars, AI can handle a large share of the work for a small business. Strategy, creative judgment, and knowing your local market still benefit from human expertise. Many owners use AI to do the first 80 percent and then edit.

    Will AI-written content hurt my SEO?

    Google has said it rewards helpful content regardless of how it is produced. The risk is publishing thin, generic text. Add your own expertise, examples and photos to anything AI drafts.

    How do I keep the AI on brand?

    Paste the brand brief from prompt 1 at the start of every conversation, and include two or three examples of past content you like.

  • 10 ChatGPT Prompts for Salary Negotiation (Scripts, Emails and Role-Play)

    Many US job seekers accept the first offer they receive, even though employers often expect some negotiation and leave room for it. The hard part is not knowing what to say. These 10 prompts turn ChatGPT, Claude or Gemini into a negotiation coach that helps you research, plan, rehearse and write every message, from the first counteroffer to negotiating a raise with your current employer.

    AI does not know real-time salary data for your exact role and city. Research market pay yourself using sources such as the US Bureau of Labor Statistics, pay ranges listed in job postings (now required by law in several states, including California, Colorado, New York and Washington), Levels.fyi for tech roles, and conversations with people in your field. Then give that data to the AI.

    Step 1: Prepare

    1. Build your negotiation brief

    You are an experienced US compensation negotiation coach.
    
    Help me prepare to negotiate this offer:
    - Role: [Job Title] at [Company], [City or Remote]
    - Offer: base [Base Salary], bonus [Bonus], equity [Equity], PTO [PTO], start date [Date]
    - Market data I found: [Market Range and Sources]
    - My current or previous pay: [Current Pay or "prefer not to share"]
    - My leverage: [Competing offers, rare skills, strong interview feedback]
    - What matters most to me, ranked: [Priorities]
    
    Give me: my target number, my walk-away number, a justification for the target in 2 sentences, which non-salary items to ask for if base is capped, and the biggest risk in my plan.

    Why it works: Negotiation is mostly preparation. Ranking your priorities lets the AI suggest trade-offs, like a signing bonus or extra PTO when the base salary band is fixed.

    2. Anticipate the employer’s position

    Based on this information about the company and role, explain how the hiring manager and recruiter are likely thinking about my offer: [Company Size, Industry, How Long the Role Was Open, Any Signals From the Interviews]
    What constraints might they have? Where are they most likely to have flexibility? What would make them say yes quickly?

    Step 2: Make your counteroffer

    3. The counteroffer email

    Write a counteroffer email to [Recruiter Name] for the [Job Title] offer.
    - Open by expressing genuine enthusiasm for the role
    - Ask for [Target Salary] base, justified by [Justification]
    - Mention [Other Ask, e.g. signing bonus or remote days] as a secondary request
    - Confident, warm, never apologetic or demanding
    - Under 180 words, no phrases like "I was hoping" or "if possible"
    Then give me a shorter version I can say on a phone call.
    Weak prompt result
    “Hi, thank you so much for the offer! I was just wondering if there is any chance the salary could maybe go a little higher? Totally understand if not!” (Apologetic, no number, invites a no.)
    Engineered prompt result
    Thanks the recruiter, restates excitement about a specific project, names a precise base salary, gives a one-sentence reason grounded in market data and the scope discussed in interviews, and closes by saying they are ready to sign at that number.

    4. Phone script with pauses

    I will negotiate my offer by phone. Write a natural script for me, including: how to open, exactly how to state my number ([Target Salary]), when to pause and stay silent, and how to respond if they say "that's above our range", "we need an answer by Friday", or "what's your current salary?". Keep my lines short and spoken, not formal.

    Practice this out loud. The pause after stating your number is the part people find hardest and the part that works best.

    5. Role-play the negotiation

    Role-play as a recruiter at [Company] who has a budget ceiling of [Hidden Ceiling, or "pick a realistic one and don't tell me"]. I will negotiate for the [Job Title] offer. Push back realistically, use common recruiter tactics, and stay in character. After 6 exchanges, step out of character and give me feedback: what I did well, where I left money on the table, and a better phrasing for my weakest moment.

    Step 3: Handle the response

    6. Respond to “this is our best offer”

    The recruiter replied: "[Paste Their Reply]".
    My priorities are [Priorities] and my walk-away number is [Walk-Away].
    Give me 3 response options: (1) accept gracefully, (2) accept base but ask for one non-salary item, (3) politely hold firm with a final ask. For each, write the email and explain the risk.

    7. Compare two offers

    Compare these two job offers in a table, including total first-year compensation, 4-year value of equity (assume no growth, and also show a 2x scenario), benefits value, commute or remote costs, and career growth factors I describe:
    Offer A: [Details]
    Offer B: [Details]
    My priorities: [Priorities]
    Then write a short email to the company I prefer using the other offer as leverage, honestly and professionally.

    Negotiating a raise at your current job

    8. Build your raise case

    Help me build a case for a raise. I am a [Job Title] and have been at [Company] for [Time].
    My accomplishments this year with results: [Accomplishments]
    Responsibilities I took on beyond my role: [Extra Responsibilities]
    Market pay data: [Market Data]
    My current salary: [Salary]. Target: [Target].
    Create a one-page brief I can bring to my manager: summary, 4 evidence points, the ask, and answers to "budgets are frozen" and "let's revisit at your review".

    9. Request the raise meeting

    Write a short message to my manager [Manager Name] asking for a 30-minute meeting to discuss my compensation and growth. Professional, positive, not a surprise ambush, under 70 words.

    10. Plan B if the answer is no

    My manager said no to a raise because [Reason]. Help me respond professionally and ask for a concrete path: specific goals, a timeline for revisiting, and anything non-monetary that is possible now ([Ideas: title change, training budget, flexible schedule]). Write my reply and a follow-up email that documents what we agreed.

    Tips for a stronger negotiation

    • Anchor with a specific number. “$118,500” signals research. A vague range invites the low end.
    • Negotiate total compensation. Signing bonuses, equity, PTO, remote work, title and start date are often easier for a company to move than base salary.
    • Stay enthusiastic. Negotiating rarely costs you an offer when you are respectful and clearly want the job.
    • Get it in writing. Ask for an updated offer letter before you resign from your current job.

    Frequently asked questions

    Should I tell a recruiter my current salary?

    In many US states and cities, employers are legally barred from asking about salary history. Wherever you are, you can decline politely and redirect to your expectations for this role, based on market data.

    Can negotiating cause a company to withdraw an offer?

    It is rare when you negotiate respectfully. It is more likely if you make ultimatums, negotiate in bad faith, or keep reopening terms after agreeing. Use prompt 5 to practice a calm, professional tone.

    Is this financial or legal advice?

    No. These prompts help you prepare and communicate. For complex equity packages or employment contracts, consider talking to an employment attorney or a financial professional.

    Next step: still job hunting? Start with our AI resume and job search prompts.

  • 12 AI Resume and Job Search Prompts That Get You Interviews

    Most resumes are rejected in seconds, either by applicant tracking systems (ATS) or by recruiters scanning for proof that you can do the job. AI can help you tailor every application, but a lazy prompt like “improve my resume” usually produces buzzword-stuffed bullets and, worse, invented accomplishments. These 12 prompts are built around what US recruiters actually look for: relevant keywords, measurable results and honest, specific language.

    Golden rule: never let AI invent experience, numbers or credentials. Every prompt below tells the model not to fabricate, and asks it to mark missing numbers with placeholders so you can fill in the truth.

    Tailoring your resume to a job

    1. Job description keyword analysis

    You are a senior technical recruiter at a US company.
    
    Analyze this job description:
    [Paste Job Description]
    
    Give me:
    1. The 10 most important hard skills and keywords, ranked by importance
    2. The 5 soft skills or traits they emphasize
    3. What the hiring manager is most worried about (the problem this hire solves)
    4. Three questions likely to come up in the interview
    Format as a short report with headings.

    Why it works: Before rewriting anything, you need to know what the role is really asking for. Point 3 is the most valuable: it tells you the story your resume and cover letter need to tell.

    2. Gap analysis between your resume and the job

    Compare my resume to this job description.
    
    Resume:
    [Paste Resume]
    
    Job description:
    [Paste Job Description]
    
    Create a table with: Requirement, Evidence in my resume (quote it), Match (Strong / Partial / Missing), and How to address it honestly.
    Do not suggest claiming skills I do not have. For missing items, suggest related experience I might reframe or a way to mention it in the cover letter.

    3. Rewrite bullets with measurable results

    Rewrite these resume bullets for a [Target Job Title] role:
    [Paste Bullets]
    
    Rules:
    - Start each bullet with a strong past-tense action verb (no "responsible for")
    - Use the formula: action + what you did + measurable result
    - If a number is missing, insert a placeholder like [X%] or [$X] and tell me what to measure
    - Naturally include these keywords where truthful: [Keywords]
    - Max 2 lines per bullet
    - Do not invent achievements, tools or titles

    Fill this one in instantly with the resume template in our Template Builder.

    Weak prompt result
    “Responsible for managing social media accounts and creating content. Helped increase engagement.” (Duty-focused, vague, no numbers.)
    Engineered prompt result
    “Grew Instagram followers from 4,200 to 11,800 in 9 months by launching a weekly Reels series and a UGC campaign, lifting site traffic from social by [X%].” (Action verb, specific method, measurable result, honest placeholder.)

    4. ATS formatting check

    Review my resume text for applicant tracking system (ATS) problems:
    [Paste Resume Text]
    
    Check for: non-standard section headings, missing keywords from this job [Paste Key Requirements], dates in inconsistent formats, acronyms without the spelled-out version, and anything that would likely be lost in a table, header or text box.
    List each issue with a fix.

    5. Professional summary in three versions

    Write three versions of a 3-line professional summary for my resume, targeting [Target Job Title] roles.
    My background: [Years] years in [Field], key strengths [Strengths], biggest achievement [Achievement].
    Version 1: results-focused. Version 2: skills-focused. Version 3: career changer angle from [Previous Field].
    No cliches like "results-driven", "team player" or "passionate".

    Cover letters and LinkedIn

    6. A cover letter people actually read

    Write a cover letter for [Job Title] at [Company].
    Why this company specifically: [Reason]
    My two most relevant achievements: [Achievements]
    The problem they need solved (from the job post): [Problem]
    
    Rules: under 250 words. Do not open with "I am writing to apply". First line should show I understand their business. One paragraph connecting my achievements to their problem. Confident close asking for a conversation.

    7. LinkedIn headline and About section

    Write 5 LinkedIn headline options (under 220 characters) and an About section (under 1,500 characters) for a [Current Role] who wants to move into [Target Role].
    Include these keywords recruiters search for: [Keywords]
    About section: first-person, opens with a hook, 3 short paragraphs, ends with what I am looking for and how to reach me.

    8. Recruiter outreach message

    Write a LinkedIn message (under 300 characters for a connection note, plus a longer 100-word follow-up) to a recruiter at [Company] about the [Job Title] role. Mention one specific, relevant result: [Result]. Polite and direct, no flattery.

    Interview preparation

    9. Mock interview, one question at a time

    Act as the hiring manager for [Job Title] at a [Company Type] company. Here is the job description: [Paste Job Description]
    
    Interview me with 8 questions: a mix of behavioral, role-specific and one curveball. Ask one question at a time and wait for my answer.
    After each answer, score it 1-10, explain what was strong and what was missing, and show a stronger version using the STAR method based only on what I said.

    This is one of the highest-value prompts in the playbook. Answering out loud and then typing a short version is excellent practice.

    10. Build STAR stories from your experience

    Help me turn these experiences into STAR interview stories (Situation, Task, Action, Result):
    [Describe 3 Experiences Briefly]
    For each, ask me up to 2 questions to fill in missing details, then write a 90-second spoken version. Tell me which common interview questions each story can answer.

    11. Questions to ask the interviewer

    I am interviewing for [Job Title] at [Company] with [Interviewer Role]. Suggest 8 smart questions to ask at the end of the interview that show I understand the role and help me judge whether the job is a good fit. Avoid questions answered on their website.

    12. Thank-you email after the interview

    Write a thank-you email to [Interviewer Name] after my interview for [Job Title]. Reference this specific topic we discussed: [Topic]. Add one sentence reinforcing why I fit: [Fit]. Under 120 words, send-ready, with a subject line.

    Tips for using AI in your job search

    • Tailor every application. Run prompts 1 to 3 for each job you seriously want. Sending one generic resume everywhere is the most common mistake.
    • Read it out loud. If a bullet sounds like a robot wrote it, a recruiter will think so too. Edit until it sounds like you.
    • Verify every claim. You will be asked about anything on your resume in the interview.
    • Negotiate the offer. When you get one, use our salary negotiation prompts before you accept.

    Frequently asked questions

    Can recruiters tell if a resume was written with AI?

    Often, yes, when the text is generic and full of buzzwords. They rarely can when AI is used to tailor and tighten your own real, specific experience. Specific details are what make a resume credible.

    Will ChatGPT make my resume ATS-friendly?

    It can help with keywords and section headings, but formatting matters too. Use a simple single-column layout, standard headings like “Experience” and “Education”, and avoid tables and text boxes for key information.

    Is it okay to use AI for cover letters?

    Yes, as long as the content is true and you personalize it. Most employers care far more about whether the letter shows real understanding of their business than about how it was drafted.

  • 12 ChatGPT Prompts for Real Estate Agents (Listings, Follow-Ups and Marketing)

    Real estate agents spend hours every week writing: listing descriptions, follow-up texts, market updates, social posts and emails to past clients. AI can cut that time dramatically, but only if the prompt gives it the details a good agent would use. Generic prompts produce generic copy full of phrases like “nestled” and “won’t last long” that buyers skim right past.

    This playbook gives you 12 tested prompts for US real estate agents, organized by the part of the business they help with. Each one explains what to customize and why it works. They are written for ChatGPT, Claude and Gemini, and you can fill in every variable instantly with our Prompt Template Builder.

    Compliance reminder: AI does not know your state’s advertising rules or your brokerage’s policies. Always review output for Fair Housing compliance, accuracy and required disclosures before publishing. Never paste client personal information you are not permitted to share into an AI tool.

    Listing descriptions

    1. MLS listing description that follows Fair Housing rules

    You are a top-producing US real estate agent known for listing descriptions that get showings.
    
    Write an MLS listing description for:
    - Property: [Beds] bed / [Baths] bath [Property Type], [Square Feet] sq ft, built [Year]
    - Location: [Neighborhood, City, State]
    - Best features: [Top 3 Features]
    - Recent upgrades: [Upgrades with years]
    - Nearby: [Parks, transit, shopping, schools by name]
    
    Rules:
    - 250 words max. Lead with the single most compelling feature.
    - Describe the property, never the ideal buyer. Do not mention family status, religion, race, national origin, age, sex or disability, and avoid phrases like "perfect for young families" or "walking distance" that some MLSs flag.
    - No cliches: nestled, won't last long, must see, dream home, charming.
    - End with a clear call to schedule a showing.
    - Then give me a 40-word version for social media.

    Why it works: The banned-phrase list removes the filler that makes AI listings sound identical, and the Fair Housing rule keeps the AI focused on features rather than people. Upgrades with years (“roof replaced 2023”) build buyer confidence far more than adjectives do.

    2. Rewrite a listing in three styles

    Here is my current listing description:
    [Paste Description]
    
    Rewrite it three ways:
    1. Luxury: refined, understated, focused on materials and craftsmanship
    2. First-time buyer friendly: practical, focused on value, low maintenance and monthly cost drivers
    3. Investor: focused on rental potential, layout, condition and location data I provided
    
    Keep all facts identical. Do not add any feature I did not mention. Flag anything in my original that could raise a Fair Housing concern.

    Useful when a listing has been sitting and you want a fresh angle. The final instruction turns the AI into a second pair of eyes on compliance.

    3. Feature-to-benefit converter

    Turn each of these home features into a one-sentence buyer benefit. Be specific and concrete, not flowery.
    [List Features, one per line]
    Example: "Tankless water heater" becomes "Endless hot water and lower energy bills, with no tank taking up garage space."

    Lead follow-up and client communication

    4. Post-showing follow-up texts

    You are a friendly, professional real estate agent in [City, State].
    
    Write 3 follow-up text messages (under 300 characters each) to [Client First Name], who toured [Property Address] on [Day] and said: "[What They Said]".
    
    Version 1: helpful, shares one new detail about the home that addresses their comment
    Version 2: suggests looking at similar homes this weekend
    Version 3: low-pressure check-in
    
    No emojis. No pressure phrases like "act fast". Sound like a real person texting.

    Customize: The client’s own words are the most important variable. If they worried about the small backyard, version 1 can mention the park two blocks away.

    5. Revive a cold lead

    Write a short, genuine email to a buyer lead who contacted me [Time Ago] about homes in [Area] and then went quiet. Their original budget was around [Budget] and they wanted [Must-Haves].
    
    Share one useful local market fact I provide here: [Market Fact]
    Ask one easy question they can answer in a word.
    Under 120 words. No guilt-tripping, no "just checking in".

    6. Explain a confusing process to a first-time buyer

    Explain [Process, e.g. earnest money / appraisal gap / inspection contingency] to a first-time home buyer in [State].
    
    - Use plain language and one everyday analogy
    - Explain what happens, who pays, and what can go wrong
    - Keep it under 250 words
    - End with: "Rules vary by contract and state, so let's go over your specific situation."
    Do not give legal advice. If state rules commonly differ, say so.

    Marketing and lead generation

    7. Monthly market update email

    You are a real estate agent writing a monthly market update for past clients and your sphere in [City or Neighborhood].
    
    Data for [Month Year]:
    - Median sale price: [Price] (vs [Last Year Price] a year ago)
    - Average days on market: [Days]
    - Active listings: [Number]
    - Notable local news: [News]
    
    Write a 200-word email that explains what these numbers mean for buyers and for sellers, in plain English. Include a subject line under 50 characters. Use only the data I gave you. Do not predict future prices.

    Important: Always paste your own MLS data. AI models do not have reliable, current local market statistics, and invented numbers can damage your credibility.

    8. Seven days of social posts for one listing

    Create a 7-day Instagram and Facebook content plan to promote [Property Address], a [Property Summary].
    
    For each day give: the post angle, the caption (under 150 words), and a photo or video idea.
    Mix: feature spotlight, neighborhood, open house reminder, behind the scenes, a quick tip for buyers, and a "just listed" post.
    Include the open house date: [Open House Date and Time].
    Add 5 relevant local hashtags at the end of each caption.

    9. Neighborhood guide for your website

    Write a 700-word neighborhood guide for [Neighborhood, City, State] for people considering moving there.
    
    Use these facts I have verified: [Paste Facts: parks, restaurants, commute times, events, housing styles, price range]
    
    Structure: overview, housing types and typical price range, things to do, getting around, who tends to love it (describe lifestyle preferences, not demographics), and a closing call to contact me.
    Write in a warm, local-expert tone. Do not invent business names or statistics.

    Before and after: listing description

    Weak prompt result
    “Welcome to this charming 3-bedroom home nestled in a quiet neighborhood! This must-see property features a spacious kitchen and a lovely backyard, perfect for families. Won’t last long!” (Vague, cliche-heavy, and it describes the buyer instead of the home.)
    Engineered prompt result
    Opens with the 2024 chef’s kitchen and quartz island, mentions the new roof and HVAC with years, names the park and trail nearby, and ends with a showing call to action. 230 words, no cliches, no buyer descriptions.

    Business and productivity

    10. Listing presentation talking points

    I have a listing appointment with a homeowner in [Area] who is deciding between me and [Number] other agents. Their main concern is [Concern].
    
    My strengths: [Your Experience, Stats, Marketing Approach]
    Write: a 60-second opening, 5 talking points that address their concern with my real numbers, and answers to these objections: "Another agent offered a lower commission" and "We want to list higher than your suggested price."

    11. Turn a voice memo into a client recap

    Turn this rough voice-memo transcript from a client meeting into a clear recap email for the client: [Paste Transcript]
    Include: what we discussed, decisions made, next steps with dates, and what I need from them. Friendly and professional, under 200 words.

    12. Review request after closing

    Write a short, warm message to [Client Name], who just closed on [Property or Area], thanking them and asking for a review on [Platform]. Mention one specific moment from the transaction: [Moment]. Include the review link placeholder [Link]. Under 90 words.

    How these prompts behave in ChatGPT, Claude and Gemini

    • ChatGPT tends to write energetic marketing copy. The banned-cliche list in prompt 1 matters most here.
    • Claude usually follows compliance instructions closely and is strong at flagging risky phrasing in prompt 2.
    • Gemini can pull in web information. That is helpful for general neighborhood ideas, but always verify any business names, school details or statistics it adds.

    Frequently asked questions

    Can I use AI-written listing descriptions on the MLS?

    Generally yes, but you remain responsible for accuracy and compliance. Check your MLS rules, your state real estate commission’s advertising rules, and your brokerage policy. Many agents use AI for a first draft and then edit it.

    Is it safe to paste client details into ChatGPT?

    Avoid pasting sensitive personal information such as financial details, Social Security numbers or anything covered by a confidentiality agreement. Use first names or placeholders, and check your AI tool’s data settings.

    Which AI model is best for real estate agents?

    All three major assistants handle these prompts well. Pick the one you will use daily, and spend your effort on the details you feed it. Try any prompt in our Prompt Enhancer to adapt it for your preferred model.