Prompt library · AI · 16 prompts
Prompts from the guide
Research before a big purchase, in five minutes
16 prompts from this guide. Fill in whatever sits in [square brackets] — your own context, the document text or the name of your tool. That context is exactly what separates a generic answer from a usable one.
Have an interview drag your criteria out of you
I'm about to buy [what], and I want to first get clear on what I should actually be choosing by. Don't give me any specific models or recommendations yet. What I know about my situation: [budget], [space and constraints], [how often and for what I'll use it], [what bugged me about what I have now], [how long it needs to last]. Ask me 8 questions whose answers would substantially change what I should buy. Ask about things people usually don't think about for this kind of purchase and then regret — not things I'd read in any article. Ask one question at a time, wait for my answer, and only then move to the next. At the end, turn all my answers into a list of my criteria, ranked by importance.
What you probably overlooked
I'm about to buy [what] for [use case] with a budget of [amount]. My criteria: [list]. Tell me what I've most likely overlooked for this purchase. Split it into three groups: 1. Costs that aren't in the sticker price (delivery, installation, consumables, running costs, insurance, service, disposing of the old one) 2. Things that only show up after six months of use and don't appear in first-week reviews 3. Situations where my choice would turn out to be wrong — what would have to happen for me to regret it One sentence per point on why. No specific models, just what to look at.
Weights: what's a must-have and what's nice-to-have
Here's my list of criteria for buying [what]: [paste the list] Sort them into three groups, with one sentence per item on why: A) Dealbreakers — if a candidate fails this, it's out no matter what else B) Deciding factors — these are what choose between the ones that remain C) Bonus — nice to have, doesn't affect the decision Be strict about group A: if there are more than three items in it, tell me which of them don't actually belong there, because they wouldn't stop me if everything else fit. For group B, suggest percentage weights that add up to one hundred, and justify them.
Without web search turned on, it isn't research
Search the web and prepare candidates for me to buy: [what]. My dealbreaker criteria (rule out anything that fails these): [list from group A] My deciding criteria: [list from group B] Budget: [amount], buying in [my country], I need it by [when]. Find 6 to 10 specific models that meet the dealbreaker criteria. For each one: - the exact designation, including the full model code (variants often differ only by the number after the dash and have different specs) - values for my deciding criteria - a source link for EVERY parameter — ideally the manufacturer's own page - an approximate price range and a link to where you got it, with a date - year of release and whether it's the current lineup or a model being phased out Rules: - don't invent any model; if you're not sure it exists in this exact variant, say so - where you can't find a parameter, write UNKNOWN, don't fill it in with a guess - at the end, list which of my criteria you weren't able to verify, and why
Deep research for big purchases
Do deep research on buying [what] in the [range] price bracket for [use case]. Market: [my country]. I want a report covering: 1. How this category is segmented today — what you actually get for what money, and where the point is beyond which you start overpaying for things an average user won't use 2. Which specs are marketing and which have a real effect on day-to-day use — explain why for each one 3. An overview of brands: reputation, availability of service and spare parts in [my country], typical weaknesses 4. Independent tests and expert reviews from the last two years, with links — and distinguish lab tests from first-week impressions 5. What's coming in this category: is there a risk that a new lineup shows up in three months and this one drops in price Cite a source and date for every claim. Where sources disagree, show both views instead of picking one.
Phase 3: a comparison table built around your columns
From the candidates you found, build a comparison table. Columns, in this order: 1. Model (exact designation) 2. Approximate price and the date it applied 3. [my criterion 1] 4. [my criterion 2] 5. [my criterion 3] 6. Extra costs in the first year (delivery, installation, consumables, running costs) 7. Three most common user complaints 8. Source link for the main parameters Sort the rows by how well they fit my deciding criteria and their weights, not by price. Below the table, write: - which two models are most similar, and what difference between them is significant enough to matter - which model is the best choice if I want to save money, and what I'd give up for that - which one, if I can go up to the top of my budget, and what extra I'd get for it - whether there's a type of solution missing from this shortlist that I hadn't considered at all Leave cells blank where you don't have a verified value. Don't fill anything in with a guess — an incomplete table beats a tidy but false one.
A table you can actually move around in
Turn this comparison table into an interactive artifact: [paste the table, or refer back to the previous message] Features: - sliders for the weight of each criterion (always adding up to 100%) - automatic recalculation of the overall score and candidate ranking - a toggle that hides models failing the dealbreaker criteria - an expandable section for each candidate with complaints and links - a field for manually editing the price, so I can plug in a current offer I found myself Enter the data in the code exactly as it is in the table, including blanks — don't fill in missing values. Calculate the score only from criteria that are filled in, and show how many values are missing for each candidate.
Phase 4: the complaints section
Search for what users complain about on these specific models: [list of finalists with exact designations] Search seller reviews, forum threads, comments under reviews, and user tests. For each model: 1. The five most frequently repeated complaints, ranked by how often they show up 2. For each one: how often it repeats (a single mention, or does it run across multiple sources), how long into ownership it shows up, and whether it's a defect in one unit or a trait of the model 3. At least one source link per complaint 4. What users repeatedly praise, on the other hand At the end, one sentence per model: who this model is a bad choice for. Don't generalize from one furious review. If a complaint is a one-off, say so.
How to read what comes back
Here are the complaints you found for model [model]: [paste the list] Sort them for me into four groups: A) A design flaw in the product — repeats across sources and is about how the thing is built B) A problem with one unit or a bad batch — bad luck, can be fixed through a warranty claim C) A problem with the seller or shipping — unrelated to the product itself D) A misunderstanding or misuse — the user expected something the product was never designed to do For group A, tell me whether it applies to my way of using it ([usage description]) — or whether I'd avoid it based on how I'll actually use it. For group D, tell me what those people were expecting, and whether I might be expecting the same thing without realizing it.
Have your own choice picked apart
I've decided to buy [model] for [price] for [use case]. My criteria were: [list]. Don't confirm this for me. Play the role of someone trying to talk me out of this purchase, and write: 1. Three specific reasons this is the wrong choice for my particular use case 2. What I'd buy instead for the same money — two specific alternatives, including one from a completely different category of solution 3. What I'm overpaying for here that I won't actually use 4. What I should instead spend more on, because skimping on that particular spec doesn't pay off 5. When it makes sense to delay the purchase — is a new lineup coming, seasonal discounts, or any other reason to wait Be specific and back it up with actual specs, not generic advice. At the end, tell me whether, after all that, my choice still holds up.
Five questions for the seller
I'm about to buy [model] from [seller / any seller]. Prepare questions I need to answer myself or verify with the seller before I pay. Split them into: 1. Questions for the seller (stock availability, exact model variant, all-in price, delivery and installation, hauling away the old one, warranty and its terms, where the nearest authorized service center is) 2. Things I need to verify myself at home (dimensions including hookups and door clearance, connections, compatibility with what I already have, weight limits, whether it fits through the apartment) 3. Questions that decide whether to buy now or wait For each question, write one sentence on what a bad answer looks like and why — so I can recognize when someone's holding something back. Ten questions total, maximum, so I can actually bring them with me.
Cars
I'm considering buying [model, year, engine, mileage] for [price]. Usage: [km per year, city/highway mix], I'll keep it for [number] years. Estimate my cost of ownership over that period: - mandatory liability and collision insurance (an order-of- magnitude range, not a specific quote) - scheduled servicing per the manufacturer's plan, and what it covers - wear parts that will come due in that time (timing belt, clutch, brakes, shocks, tires) and roughly what the parts and labor cost - fuel or energy use for my driving profile - road tax, inspection, and any other applicable fees - an estimate of resale value at the end Separately, list: 1. Typical weaknesses of this exact engine and generation, with a source link 2. What to have checked before buying, and what to ask the previous owner 3. Which documents I want to see (service book, mileage history, proof of origin) For every number, state where it comes from and how reliable it is. I'll verify prices with a mechanic myself — I just want an order-of-magnitude sense.
Appliances and electronics
Compare [list of finalists] in terms of lifespan and repairability, not specs. For each one: - how long the manufacturer guarantees spare-parts availability - is there authorized service in [my country], and how many locations - what the most common failures are, and how long into ownership they show up - the approximate cost of the most common post-warranty repair, compared to the price of a new unit - can it actually be repaired, or is it glued together and gets thrown out when something breaks - warranty length, and whether the manufacturer offers an extension, for how much At the end, tell me which of these models has the best ratio of price to likely lifespan, and why. Cite a source for every value; where you don't have one, write UNKNOWN.
Insurance
Compare these [type] insurance offers for me: [paste the offers, ideally including the policy conditions] My situation: [what I'm insuring, where, how I use it, what I'm specifically worried about]. A table with columns: offer | annual premium | deductible | payout limit for [thing I care about] | limit for [another thing] | is roadside/emergency assistance included, and what it covers Below the table: 1. EXCLUSIONS: what each offer does NOT cover. Go through the full policy conditions, not just the summary sheet, and cite the clause for every exclusion. 2. Obligations I have to meet to be eligible for a payout (security measures, reporting deadlines, documentation) 3. Three specific situations from my description, and for each: which offers would pay out and which wouldn't, and why 4. The offer that looks cheapest — why is that? A higher deductible, lower limits, or broader exclusions? Point 3 is the most important — spend the most space on it.
Energy providers
Compare these [electricity / gas] provider offers for me: [paste the offers] My usage: [kWh or m3 per year], tariff [tariff], [number] of metering points. For each offer, calculate the TOTAL annual cost, broken down into: - usage charges (unit price × my consumption) - fixed monthly charges per metering point - regulated components, if the offer lists them - one-time fees for switching providers Then, for each offer, list: 1. Length of commitment and the price-lock period — until when the stated price applies 2. What happens once the price lock ends (switching to a standard rate, automatic renewal, and under what conditions) 3. Penalties for early cancellation and under what circumstances they apply 4. Can the provider change the price during the lock period? Under what conditions? 5. Conditions I have to meet for the offered price to apply (direct debit, paperless billing, bundling another product) At the end: which offer comes out best over the whole commitment period, not just the first year. State which numbers you're calculating from, so I can redo the math myself.
Plans and subscriptions
Here's a list of my recurring payments for services and subscriptions: [paste the list: name, monthly amount, what I get for it, how often I actually use it] Turn this into an overview: 1. Total annual cost, broken down by category 2. Rank the items by the ratio of “what I pay” to “how often I use it” — worst first 3. For each item: is there a cheaper equivalent (a lower tier, annual billing instead of monthly, a family plan, a student rate), and what would I lose by switching 4. Which two items overlap and do the same thing 5. Which ones are locked into a commitment, and until when — and which ones I can cancel right now At the end, suggest three specific actions, with an estimated annual saving for each, ranked by the ratio of saving to effort.