AI prompts for freelancers

Write my proposal for this freelance job.

THE JOB POST: [PASTE THE FULL POST]
MY RELEVANT EXPERIENCE: [PROJECTS, RESULTS, SKILLS - only true ones]
PORTFOLIO LINKS: [LINKS]
MY RATE / BID: [AMOUNT]
PLATFORM: [e.g. Upwork, Fiverr request, Freelancer, LinkedIn]

Write a proposal that:
- Opens with the client's problem in my own words, showing I read the post (not "Dear Sir/Madam, I am a hardworking...")
- Answers any questions the client asked, in order
- Gives ONE directly relevant example with a result
- Proposes a short plan: first 3 steps and a timeline
- Asks one smart question that shows understanding
- Stays under 150 words (clients skim many proposals)

Also give: 2 alternative opening lines, and red flags in the job post I should be careful about (unclear scope, payment outside the platform, free test work).

Help me set my freelance / consulting rates.

WHAT I DO: [SERVICE]
MY EXPERIENCE: [YEARS, SPECIALISM, RESULTS]
MARKET / CLIENTS: [WHO AND WHERE]
TARGET YEARLY INCOME BEFORE TAX: [AMOUNT AND CURRENCY]
BUSINESS COSTS PER YEAR: [SOFTWARE, EQUIPMENT, INSURANCE, ETC.]
REALISTIC BILLABLE HOURS PER WEEK: [HOURS]
WEEKS OFF PER YEAR: [WEEKS]
WHAT OTHERS CHARGE (if known): [RANGE]

Calculate, showing the arithmetic:
1. My minimum hourly rate to hit the target (target + costs / billable hours per year)
2. A day rate and a half-day rate
3. Three project price examples for typical jobs: [DESCRIBE 2-3 TYPICAL JOBS]

Then:
- Compare with the market range I gave and say whether I am under, within or over
- Suggest when to use hourly, day or fixed-price, and the risks of each
- Write 2 sentences I can use when a client asks "why this price?"
- Point out any assumption that looks unrealistic (e.g. 40 billable hours a week is rarely achievable)

Write a client quote.

CLIENT: [NAME/TYPE]
WHAT THEY ASKED FOR: [THEIR REQUEST, IN THEIR WORDS]
WHAT I WILL ACTUALLY DELIVER: [YOUR SCOPE]
PRICE AND BASIS: [AMOUNT, AND WHETHER FIXED / DAY RATE / MILESTONE]
TIMELINE: [DURATION AND ANY DEPENDENCIES ON THEM]
WHAT I NEED FROM THEM: [ACCESS, CONTENT, APPROVALS, DECISIONS]
CURRENCY AND PAYMENT TERMS: [DETAIL]

Structure:
1. Understanding - their problem in their words, two sentences. Shows you listened.
2. What is included - specific deliverables, each with a one-line description of what 'done' means
3. What is not included - the adjacent things they will assume are in. Be thorough; this section prevents the argument.
4. What I need from you - with dates, and what happens to the timeline if each is late
5. Timeline - phases with dates, marking which depend on their input
6. Price - the number, what it covers, and what triggers an additional charge
7. Revisions - how many rounds are included and what counts as a revision versus a new request
8. Payment terms - schedule, method, late terms
9. Validity - how long this quote stands

Rules:
- Section 3 must be specific. 'Additional work' is not an exclusion; 'migration of historical data prior to 2024' is.
- Section 7 is where fixed-price work goes wrong. Define a revision precisely.
- No hourly estimates unless the basis is a day rate.
- Under 700 words.

Write a payment chase.

CLIENT: [NAME/TYPE OF CLIENT]
INVOICE: [NUMBER, AMOUNT, ORIGINAL DUE DATE]
DAYS OVERDUE: [NUMBER]
PREVIOUS CHASES: [NONE / DATES AND WHAT WAS SAID]
RELATIONSHIP: [new client / long-standing / ending / we want more work from them]
OUR LEVERAGE: [e.g. work in progress we could pause, contractual late fees, nothing]
ANY REASON THEY MIGHT HAVE: [dispute, cashflow, process, unknown]

Write the message appropriate to this stage:
- Under 10 days overdue: assume process, not refusal
- 10-30 days: assume it needs a person, name one, ask for a date
- 30-60 days: state consequences plainly, once
- Over 60: formal, reference the contract term, state next step and date

The message must:
- Lead with the invoice number and amount in the first line
- Ask one specific question that can be answered in one line ('can you confirm the payment date?' not 'can you look into this?')
- Give them an easy out if the reason is process (wrong PO, wrong contact, missing detail)
- State the next step and when it happens
- Be under 120 words

No 'hope you are well', no 'just checking in', no exclamation marks, no apology for chasing.

Also give me the follow-up message for if this gets no reply in 7 days, and the point at which I should stop emailing and call.

Write a change request.

PROJECT: [NAME]
WHAT IS BEING REQUESTED: [THE CHANGE]
WHO IS ASKING: [ROLE]
WHY THEY WANT IT: [THEIR REASON]
CURRENT STATE: [WHERE THE PROJECT IS, TIMELINE, BUDGET]

Produce:

1. THE REQUEST - one paragraph, stated in the requester's terms, fairly. Steelman it.
2. THE CASE FOR - the strongest version of why this should be approved.
3. IMPACT - a table: Dimension | Effect | Confidence. Cover: timeline, effort, cost, risk, other workstreams, things that would have to be cut, and effect on the original success criteria.
4. OPTIONS - at least three: (a) approve as requested, (b) a reduced version that captures most of the value, (c) defer to a later phase, (d) reject. For each: what it costs, what it delivers, and who will be unhappy.
5. RECOMMENDATION - one option, with reasoning in three sentences.
6. THE DECISION - who must make it, by when, and what happens automatically if they do not decide by then.

Rules:
- Section 2 must be written as its advocate would write it, not as a strawman.
- Never present 'approve' and 'reject' as the only options.
- Section 6's default must be a real default. 'It waits' is a valid answer; 'it stays open' is not.

Write a project brief.

PROJECT: [NAME]
PROBLEM WE ARE SOLVING: [DESCRIPTION]
WHO HAS THIS PROBLEM: [USERS/STAKEHOLDERS]
HOW WE WILL KNOW IT WORKED: [SUCCESS MEASURE]
DEADLINE AND WHY: [DATE AND THE REAL REASON]
BUDGET/RESOURCE: [DETAIL]
DECISION MAKER: [WHO SIGNS OFF]

Structure:

1. PROBLEM - two sentences. The problem, not the solution.
2. WHY NOW - what changes if we do nothing for six months. If the answer is 'nothing much', say so.
3. SUCCESS CRITERIA - maximum three, each measurable, each with a target and a measurement method.
4. IN SCOPE - specific deliverables.
5. OUT OF SCOPE - this section must be at least as long as 'in scope'. List the adjacent things people will assume are included. Be aggressive.
6. ASSUMPTIONS - what must be true for this plan to hold. Each with an owner who will verify it.
7. DEPENDENCIES - other teams or systems, with what we need from each and by when.
8. DECISION RIGHTS - who decides what. Specifically: who can change scope, who can move the date, and who can stop it.
9. WHAT WE ARE NOT DOING INSTEAD - the opportunity cost. What is not getting done because of this.

Rules:
- Section 5 must not be shorter than section 4.
- Success criteria must not include 'launch' or 'deliver'. Shipping is not success.
- Anything I have not told you: mark [TO CONFIRM] with the question to ask.

Write a case study.

CUSTOMER: [WHO THEY ARE - INDUSTRY, SIZE]
THEIR SITUATION BEFORE: [THE PROBLEM, WITH SPECIFICS]
WHAT THEY TRIED FIRST: [IF ANYTHING]
WHAT WE DID: [THE SOLUTION]
RESULTS: [NUMBERS, WITH TIMEFRAMES]
QUOTES AVAILABLE: [PASTE ANY]
WHAT WAS HARD ABOUT IT: [HONESTLY]
AUDIENCE FOR THIS CASE STUDY: [WHO WE WANT TO PERSUADE]

Structure:
1. THE RESULT - lead with the outcome and the number. Not 'Company X was founded in 1998'.
2. WHO THEY ARE - two sentences, enough for the reader to recognise themselves.
3. THE PROBLEM - specific and concrete. What was actually happening day to day, what it cost, what they had tried.
4. WHY IT WAS HARD - the constraints, the failed attempts, what made this non-trivial. A problem that sounds easy makes the solution sound unimpressive.
5. WHAT WE DID - the actual approach, with enough detail that a similar reader could judge whether it applies to them. Include what did not work.
6. THE RESULTS - with timeframes and the measurement method. 'Response time improved 40% within three months, measured by X.'
7. WHAT THEY SAY - real quotes. Use the awkward, specific ones over the polished ones.
8. WHO THIS APPLIES TO - and honestly, who it would not.

Rules:
- Never a percentage without a baseline. '300% increase' from what?
- State the measurement period and method for every number
- Include at least one honest difficulty. Case studies with no friction read as fiction and are discounted entirely.
- No superlatives, no 'game-changing', no 'seamless'
- Do not invent quotes. Use only what I gave you, marked [NEED QUOTE] otherwise.
- If my results are thin, say so rather than inflating them

Write a follow-up.

WHO: [ROLE AND COMPANY]
WHAT HAPPENED LAST: [THE LAST CONTACT AND WHAT WAS SAID]
HOW LONG AGO: [TIMEFRAME]
HOW MANY TIMES I HAVE FOLLOWED UP ALREADY: [COUNT]
WHAT THEY SAID THEY WOULD DO: [IF ANYTHING]
WHAT I WANT: [THE OUTCOME]
WHAT I HAVE THAT COULD BE USEFUL TO THEM: [CONTENT, INTRODUCTION, INFORMATION, ANSWER]

Produce:

1. THE READ - based on how long it has been and what was said, what is probably happening? Usually one of: it is not a priority, the internal champion lost support, the budget went elsewhere, they are dealing with something else, or it is a no they have not said.

2. THE FOLLOW-UP - which must add something. Options in order of preference:
   - Useful information relevant to their stated problem
   - An answer to something left open last time
   - A relevant change in circumstances
   - The direct question

   Under 60 words. No summary of previous emails.

3. THE BREAKUP EMAIL - if I have followed up more than three times, the right move is to close the loop gracefully. Write it: state that you will stop, leave the door open without pressure, and make it easy to reply. This email gets a higher reply rate than any nudge, because it removes the obligation.

4. WHEN TO STOP - given my follow-up count, say plainly whether to continue. Continuing past a certain point damages the relationship and your reputation more than the deal is worth.

5. THE CHANNEL QUESTION - whether email is still right, or whether a call, a message on another platform, or going quiet for two months is better.

6. WHAT NOT TO DO - no 'just bumping this', no 'following up on my previous email', no 'did you see my last message', no guilt, no fake deadline, no 'should I close your file?' as a manipulation.

Rules:
- Never send a follow-up whose only content is that you sent a previous one
- If I have nothing to add, say so and recommend waiting rather than writing

Help me write an email I have been avoiding.

WHO IT IS TO: [RELATIONSHIP AND CONTEXT]
WHAT I NEED TO SAY: [THE MESSAGE]
WHY IT IS DIFFICULT: [awkward / bad news / saying no / admitting a mistake / asking for something / raising a problem]
WHAT I WANT TO HAPPEN: [OUTCOME]
HISTORY: [ANYTHING RELEVANT ABOUT PREVIOUS EXCHANGES]
MY DRAFT IF I HAVE ONE: [PASTE]

Write the email so that:
- The main point is in the first two sentences. Difficult emails get worse the longer they take to arrive at the point.
- The reason is given once, briefly. Over-explaining reads as guilt and invites negotiation.
- Any apology is specific and singular. One apology for the actual thing, not a repeated apology for existing.
- What happens next is stated concretely.
- It is under 150 words.

By type:
- SAYING NO: decline in the first sentence, give one reason, offer an alternative only if you mean it, do not leave a door open you intend to close
- BAD NEWS: the news first, then the context, then what you are doing about it. Never bury it in paragraph three.
- ADMITTING A MISTAKE: what happened, the impact, what you are doing, what prevents recurrence. No excuses mixed in with the apology.
- ASKING: the ask early, why them, what it involves specifically, an easy way to decline
- RAISING A PROBLEM: the observable facts, the impact, what you want to happen. No interpretation of motives.

Then tell me:
- WHAT I AM AVOIDING SAYING - if my draft or description dances around something, name it
- THE SENTENCE MOST LIKELY TO BE MISREAD, and the safer version
- WHETHER THIS SHOULD BE AN EMAIL AT ALL - some of these are conversations. Say so if it is.

Help me write a one-page business plan.

BUSINESS: [WHAT YOU SELL OR WILL SELL]
CUSTOMERS: [WHO BUYS AND WHY]
WHERE AND HOW YOU SELL: [shop, online, WhatsApp, marketplace, B2B]
PRICES AND COSTS (as known): [NUMBERS]
COMPETITORS: [WHO ELSE CUSTOMERS COULD BUY FROM]
MONEY AVAILABLE: [BUDGET]
GOAL FOR THE NEXT 12 MONTHS: [GOAL]

Produce one page with:
1. The problem and who has it
2. The offer and why customers would choose it over the alternatives
3. How customers find and buy it
4. The money: price, cost per unit or job, gross margin (show arithmetic), monthly fixed costs, and how many sales to break even
5. The 3 biggest risks and how to reduce each
6. A 90-day action plan with weekly milestones
7. The 3 numbers to track every week

Rules: use my numbers only; mark missing ones [NEED NUMBER]. Keep it to one page - cut, do not cram.

Help me plan my week.

WHAT I NEED TO GET DONE: [LIST, WITH ROUGH TIME FOR EACH IF YOU KNOW]
FIXED COMMITMENTS: [APPOINTMENTS, WORK HOURS, ANYTHING UNMOVEABLE]
WHEN I WORK BEST: [morning / afternoon / evening / varies]
WHAT USUALLY GOES WRONG: [WHAT DERAILS YOUR WEEKS]
ENERGY THIS WEEK: [normal / low / stretched]

Produce:

1. THE TIME AUDIT - total hours in the week, minus sleep, minus fixed commitments, minus the ordinary business of living (eating, travel, household). What is genuinely left. This number is always smaller than people assume and is the reason plans fail.

2. THE TASK TIME - my list with realistic durations, which for most tasks is longer than the estimate. Say the total and compare it to the available hours. If it does not fit, say so now.

3. WHAT COMES OUT - if it does not fit, what gets deferred, delegated or dropped. Deciding this now beats discovering it on Thursday.

4. THE SCHEDULE - specific, with tasks placed at times. Demanding work at my best hours; admin and low-concentration tasks at the rest. Most people schedule by deadline and get this backwards.

5. THE BUFFER - at least a fifth of the available time unscheduled. Things overrun, things come up, and a plan with no slack breaks on the first interruption and is then abandoned entirely.

6. THE BATCHING - similar tasks grouped, because switching between different kinds of work costs more time than people account for.

7. THE DERAILMENT PLAN - I said what usually goes wrong. For each: what to do when it happens, so the week bends rather than breaks.

8. THE MINIMUM WEEK - if energy is low or things go badly, the reduced version: what must happen and what can slide. Having this defined prevents a bad Tuesday becoming a lost week.

9. THE ONE THING PER DAY - for each day, the single item that makes the day a success. Everything else is a bonus.

10. THE FRIDAY CHECK - five minutes to see what happened and adjust next week's assumptions.

Build me a small web tool as a single HTML file I can open in a browser.

WHAT IT SHOULD DO: [e.g. calculate loan repayments / convert units / split a bill / track daily water intake / estimate project cost]
INPUTS: [LIST THE FIELDS THE USER ENTERS]
OUTPUTS: [WHAT IT SHOULD SHOW]
FORMULA OR RULES (if I know them): [DETAILS, or "please suggest and explain"]
LOOK: [simple / colourful / dark mode], works on phones

Requirements:
- One file: HTML, CSS and JavaScript together, no external libraries or internet needed
- Clear labels, input validation (no negative numbers where that makes no sense), and helpful error messages
- Results update when I press a button (or live, if simple)
- Explain the formula in plain language under the tool
- Comments in the code so I can change things later

After the code:
1. Tell me how to save and open it (save as .html, double-click)
2. List 5 test inputs with the expected results so I can check it works correctly
3. Suggest 3 improvements I could ask for next

If a formula is financial, medical or legal, add a note that results are estimates and should be checked with a professional.