Market Research prompts

Analyse this competitor from public information.

COMPETITOR: [NAME AND WHAT THEY DO]
MATERIAL I HAVE:
"""
[PASTE: HOMEPAGE COPY, PRICING PAGE, JOB ADVERTS, CASE STUDIES, REVIEWS, BLOG TOPICS, SOCIAL POSTS - LABEL EACH]
"""
MY BUSINESS: [WHAT YOU DO AND HOW YOU DIFFER]
WHAT I WANT TO KNOW: [YOUR QUESTION]

Produce:

1. THEIR POSITIONING AS STATED - what they claim to be, in their words.

2. THEIR POSITIONING AS REVEALED - what the evidence suggests, which is often narrower or different. Look at:
   - PRICING: reveals the customer they actually serve and their cost structure
   - JOB ADVERTS: the most honest public document any company produces. What they are hiring for reveals what they are building, what is broken, and how they are structured.
   - CASE STUDIES: who they actually sell to, not who they say they sell to
   - REVIEWS: what customers actually value and complain about
   - CONTENT TOPICS: what they think their buyers are searching for

3. THE EVIDENCE TABLE - Claim | Evidence | Source | Confidence (observed / inferred / assumed). Be strict about the distinction.

4. THEIR IDEAL CUSTOMER - inferred, specifically. Usually narrower than their marketing implies.

5. WHERE THEY ARE STRONG - and honestly, where they would beat me.

6. THEIR STRUCTURAL CONSTRAINTS - not surface complaints, but things they cannot easily change: their cost base, their existing customers' expectations, their channel, their pricing model, their funding situation. This is where durable competitive opportunity lives.

7. WHO THEY SERVE BADLY - and whether that segment is worth having.

8. WHAT I SHOULD NOT COPY - things that work for them because of their specific situation and would not work for mine.

9. WHAT I STILL DO NOT KNOW - and what public source would tell me.

Mark every inference clearly. Do not assert anything not traceable to the material I gave you.

Write customer interview questions.

WHAT I WANT TO LEARN: [YOUR RESEARCH QUESTION]
WHO I AM INTERVIEWING: [CUSTOMERS / CHURNED CUSTOMERS / PROSPECTS WHO DID NOT BUY / NON-CUSTOMERS]
MY PRODUCT: [WHAT IT IS]
WHAT I THINK I KNOW: [YOUR ASSUMPTIONS - be honest]
INTERVIEW LENGTH: [MINUTES]

Produce:

1. WHAT I AM ACTUALLY TRYING TO LEARN - restate my research question. Often the stated question ('do they like it?') is not the useful one ('what did they do instead, and why?').

2. MY ASSUMPTIONS TO TEST - from what I told you, the beliefs this research should try to falsify. Design questions that could prove me wrong, not questions that confirm me.

3. THE QUESTIONS - 10-12, in order, building from easy to sensitive. For each: the question, what you are trying to learn, and a follow-up probe.

   Follow these principles:
   - ASK ABOUT PAST BEHAVIOUR, NOT FUTURE INTENTION. 'What did you do the last time this happened?' not 'would you use a tool that...'. People are poor predictors of their own future behaviour and good reporters of their past.
   - ASK FOR SPECIFIC INSTANCES. 'Tell me about the last time' beats 'generally, how do you'.
   - ASK ABOUT THE ALTERNATIVE. What they used before, what they considered, what they would do if your product vanished tomorrow.
   - ASK ABOUT EFFORT ALREADY SPENT. What have they already tried or paid for? Money and time already spent is the strongest evidence a problem is real.

4. THE QUESTIONS NOT TO ASK - leading questions, hypotheticals, anything answerable with yes, anything that signals the answer you want, and 'would you pay for this?' which produces polite yeses and no revenue.

5. THE HARD QUESTION - the one whose answer you least want to hear, phrased so they will answer it honestly.

6. HOW TO HANDLE POLITENESS - people soften criticism to interviewers, especially founders. Give the techniques: ask about others, ask what nearly stopped them, ask what the worst part was rather than whether there was a bad part.

7. WHAT TO DO WITH SILENCE - the instruction to stop talking. The most useful answers come after the pause.

8. WHAT NOT TO DO - do not pitch, do not explain, do not defend the product, do not correct them. The moment you explain, the interview is over.

Analyse this customer research.

INTERVIEW NOTES OR TRANSCRIPTS:
"""
[PASTE ALL, LABELLED BY PARTICIPANT]
"""

NUMBER OF PARTICIPANTS: [COUNT]
HOW THEY WERE RECRUITED: [SOURCE]
WHAT I WAS TRYING TO LEARN: [RESEARCH QUESTION]
MY PRIOR ASSUMPTIONS: [WHAT YOU EXPECTED]

Produce:

1. THE SAMPLE CAVEAT FIRST - who these participants are and who they are not. Recruitment source determines what you can conclude; people recruited from your own customer list cannot tell you why people do not buy. State plainly what this sample can and cannot support.

2. THE PATTERNS - themes appearing across participants, with the count. Distinguish rigorously:
   - Said by most participants
   - Said by several
   - Said by one, vividly
   The third category is where research goes wrong; a compelling quote from one person is not a finding.

3. WHAT SURPRISED YOU - things that contradict my stated assumptions. Lead with these; confirmation is less valuable than correction.

4. BEHAVIOUR VS OPINION - separate what people said they did from what they said they think or would do. Weight the first far more heavily.

5. THE LANGUAGE - the exact words participants used for the problem, the solution and the outcome. This is your marketing copy and your keyword research, free.

6. THE CONTRADICTIONS - where participants disagreed, or where one participant contradicted themselves. Do not resolve these into a consensus. Disagreement usually means there are two segments.

7. THE UNPROMPTED MENTIONS - things raised without being asked. These carry more weight than answers to your questions.

8. WHAT NOBODY MENTIONED that you expected them to. Silence is data.

9. THE FINDINGS - ranked by confidence. For each: what it is, the evidence, how many participants, and how confident you are.

10. WHAT TO DO NEXT - and specifically, what would need more research before acting.

Do not over-conclude. With a small sample, most of this is directional. Say so.

Design a survey.

WHAT I WANT TO LEARN: [RESEARCH QUESTION]
WHO WILL ANSWER: [AUDIENCE AND HOW YOU WILL REACH THEM]
HOW MANY RESPONSES I EXPECT: [NUMBER]
WHAT DECISION THIS INFORMS: [WHAT YOU WILL DO WITH IT]
SURVEY LENGTH: [TARGET MINUTES]

Produce:

1. IS A SURVEY THE RIGHT TOOL - answered first. Surveys are good for measuring the prevalence of things you already understand. They are poor for discovering why. If my research question is a 'why', recommend interviews instead and say so.

2. THE SAMPLING PROBLEM - who will actually respond, and how they differ from who I want to hear from. Survey respondents skew toward the engaged and the annoyed. State what this sample can and cannot support before designing anything.

3. THE QUESTIONS - as few as possible. For each: the question, the answer format, and what it tells you.

   Apply these rules:
   - No leading questions. 'How helpful was X?' assumes it was helpful.
   - No double-barrelled questions. 'Was it fast and easy?' cannot be answered.
   - No jargon or internal terminology
   - Balanced scales with an equal number of positive and negative options and a neutral midpoint
   - Include 'not applicable' and 'don't know' where they are real answers, or you force false data
   - Ask about behaviour, not intention
   - Put demographic questions last
   - Never ask something you could get from your own data

4. THE QUESTION ORDER - earlier questions prime later ones. Flag any ordering effect in my survey and fix it.

5. THE ONE OPEN QUESTION - surveys should have at most one or two free-text questions, and they produce the most useful material. Write the best one for my research question.

6. THE DROP-OFF RISK - where respondents will abandon, and what to cut. Every question costs completion rate.

7. WHAT I CANNOT LEARN FROM THIS - explicitly. Managing expectations before running it prevents over-conclusion afterwards.

8. THE ANALYSIS PLAN - decided before sending. What result would lead to what decision? If no result would change your action, do not run the survey.

Point 8 is not optional. A survey with no pre-committed analysis plan becomes a hunt for a favourable number.

Help me size this opportunity.

WHAT I WANT TO SELL: [PRODUCT AND PRICE]
WHO WOULD BUY IT: [CUSTOMER DESCRIPTION]
WHERE: [GEOGRAPHY]
WHAT I KNOW: [ANY DATA YOU HAVE - market reports, your own numbers, competitor information]
WHY I AM SIZING IT: [investment decision / prioritisation / pitch]

Produce:

1. THE HONEST FRAMING - market sizing is an estimate with wide error bars, not a measurement. Say so upfront, and state that the purpose is to determine an order of magnitude, not a number.

2. BOTTOM-UP ESTIMATE - build from units: how many potential customers exist, what proportion have the problem, what proportion would pay, at what price, how often. Show every assumption on its own line with its source or the fact that it is a guess.
   This is the only estimate worth much. Do it first.

3. TOP-DOWN CHECK - if a published market figure exists, what share would you need to hit the bottom-up number? If the answer is an implausible share, the bottom-up estimate is wrong. Use top-down only as a sanity check, never as the estimate; published market figures are usually defined too broadly to mean anything for a specific product.

4. THE ASSUMPTION AUDIT - every assumption, with: the value, the basis, and the effect on the total if it is off by half or double. Rank by sensitivity. Usually two assumptions drive the whole answer.

5. THE SERVICEABLE PORTION - of the total, what can you actually reach given your channel, geography, language and sales capacity? This is far smaller than the total and is the number that matters for a decision.

6. THE REALISTIC SHARE - what share of the serviceable market is plausible in three years, given the competition. Be conservative and say what comparable businesses achieve.

7. THE RANGE - present the answer as a range with a low, likely and high case, never a single number.

8. WHAT WOULD MAKE THIS WRONG - the assumption most likely to be false, and the cheapest way to test it before committing.

9. THE DECISION CHECK - given why I said I am sizing this, does the answer actually change the decision? If the opportunity is clearly big enough or clearly too small under every case, stop analysing and decide.

Do not produce a confident number. Produce a range and its assumptions.

Help me understand why customers are churning.

CHURN DATA:
"""
[PASTE: WHO LEFT, HOW LONG THEY STAYED, WHAT THEY PAID, STATED REASON, USAGE BEFORE LEAVING]
"""

WHAT I SELL: [PRODUCT AND MODEL]
CHURN RATE: [RATE AND WHETHER IT IS CHANGING]
EXIT SURVEY RESPONSES: [PASTE, if any]
WHAT CHANGED RECENTLY: [PRICE, PRODUCT, TEAM, ANYTHING]

Produce:

1. WHEN THEY LEAVE - churn timing is the most diagnostic signal available. Group by tenure and say what each pattern implies:
   - Very early: an onboarding or expectation problem. They never got value.
   - After the first renewal: the value did not sustain, or the price was not justified on reflection
   - Long-tenured: a change on their side, or a competitor, or slow erosion
   Which pattern dominates my data?

2. STATED VS LIKELY REASONS - exit surveys collect polite answers. 'Too expensive' usually means 'not enough value for the price'. 'No longer needed' can mean 'never worked out how to use it'. Compare stated reasons with usage data where I gave it.

3. USAGE BEFORE CHURN - the strongest signal. Did they use it and stop, or never really start? These are completely different problems: the first is a product or value problem, the second is onboarding.

4. THE SEGMENTS - do churners share a source, size, plan, use case, or acquisition channel? If people from one channel churn disproportionately, the problem is acquisition, not retention.

5. INVOLUNTARY CHURN - failed payments, expired cards, and lapsed approvals. This is often a meaningful share of churn, is entirely fixable, and is usually not even measured. Ask whether I am counting it.

6. THE PREVENTABLE SHARE - honestly, what proportion of this churn was addressable, and what was always going to happen. Some churn is fine.

7. THE EARLY WARNING SIGNAL - from the usage data, what would have predicted these churns, and how far in advance. This is the most valuable output: it turns retention from post-hoc analysis into intervention.

8. THE THREE ACTIONS ranked by (preventable churn addressed / effort).

9. WHAT I SHOULD MEASURE that I am not.

Help me test whether this idea is worth building.

THE IDEA: [WHAT YOU WANT TO BUILD]
WHO IT IS FOR: [CUSTOMER]
THE PROBLEM IT SOLVES: [PROBLEM]
WHY I THINK THEY WANT IT: [YOUR EVIDENCE - be honest about how strong it is]
WHAT IT WOULD COST ME TO BUILD: [TIME AND MONEY]
WHAT THEY DO TODAY INSTEAD: [THE CURRENT SOLUTION]

Produce:

1. THE RISKIEST ASSUMPTION - of everything that must be true for this to work, the one most likely to be false and most fatal if it is. Usually one of: the problem is not painful enough to pay for, the people with the problem are not reachable, they will not change their current behaviour, or they will not pay the price that makes it viable.
   Name it. Everything else is secondary.

2. HOW TO TEST IT CHEAPLY - specific to this idea, ordered from cheapest to most expensive:
   - Talk to people who have the problem, about what they do now (a few days)
   - Find evidence of existing effort: are people already paying for a workaround, building their own, or complaining publicly? Money and time already spent is the strongest demand signal there is.
   - Offer it before building it: a landing page, a pre-order, a paid pilot
   - Deliver it manually for a handful of customers before automating anything
   - Build the smallest thing that could work

   For each: what it costs, what it tells you, and what it does not.

3. THE SIGNAL QUALITY LADDER - rank the evidence you could gather, weakest to strongest: people say it is a good idea (worthless), people say they would use it (nearly worthless), people sign up for a waiting list (weak), people spend time on it (moderate), people pay (strong), people pay again (conclusive).
   Where does my current evidence sit?

4. THE FALSE POSITIVE WARNING - the ways this test could suggest demand that is not there. Friends being encouraging, a free signup meaning nothing, a small enthusiastic group who are not a market.

5. THE KILL CRITERIA - written now: what result would tell you not to build this? Define it before testing, because afterwards you will find a reason to continue.

6. THE 'WHY NOT ALREADY' QUESTION - if this is a good idea and obviously valuable, why does it not exist? Possible answers: it does and you have not found it, it was tried and failed, it is harder than it looks, or the market is too small. Address this honestly.

7. THE HONEST VERDICT - based on the strength of my stated evidence, is this validated, promising, or wishful? Do not be encouraging.