Online Sanity Check
A broad first-pass review of how a business appears to a potential customer online.
Start here when you want a broad outside-in view before deciding whether any area needs a deeper audit.
Fill in your details and we’ll drop them in. It happens in your browser, and nothing you type is sent to us.
The prompt, explained
The boring details, for anyone interested in the engineering behind the prompt. If you just want to get on with it, here you go.
What it asks the AI to do
Determine whether the business makes sense online, can reasonably be found by people looking for its products or services, appears current and trustworthy, and makes the next customer action easy.
The actual wording, line by line. Yes, we dressed it up as code.
- 1
Language and tone
SharedKeeps the answer clear, positive and understandable. It prevents the AI from hiding simple ideas behind jargon or presenting useful criticism as a fault-finding exercise.
language-and-tone1Write in clear, unambiguous, plain English.
2Assume the reader runs a business and may have no specialist knowledge of marketing, websites, search engines, analytics or social media.
3Do not use jargon when an ordinary word or short phrase will do.
4If a technical or specialist term is genuinely necessary, use the term, explain it immediately in plain English and say why it matters here. Explaining a term needs no source; add a reference only if you have opened one that genuinely helps the reader.
5Keep the framing positive, balanced and constructive.
6Where something genuinely is working, say so before describing the issue or risk that remains. Never invent a positive.
7Do not soften a serious issue so much that it becomes unclear.
8The aim is to reduce ambiguity and create clarity.
- 2
Evidence and certainty
SharedStops the AI from presenting guesses as facts. It makes the report show what was actually found, what is a reasonable interpretation, and what could not be confirmed.
evidence-and-certainty1Use publicly available information you can actually find.
2For important factual claims, provide the source used to confirm them.
3Label claims with exactly one of these: Observed (you saw it yourself in this conversation), Inferred (your reasoning from what you saw) or Not verified. Something you looked for but did not find, or saw only in a search-result snippet rather than on the page itself, is Not verified, never Observed.
4Never present an inference as a confirmed fact.
5Do not invent missing information.
6Do not imply that you tested, visited, clicked, searched or verified something unless you actually did.
7Do not treat absence from search results as proof that something does not exist.
8Before calling information missing, open the page where a customer would expect to find it. If you could not open it, say so and do not make it a finding or an action. Before reporting a page as empty or out of date, check that you opened the main page, not a sub-page or filtered view.
9Text a tool extracts from a page can include hidden content that visitors never see. Report a visible fault only if you are confident a visitor would see it.
10If your tools cannot show part of a page, such as its code or anything behind a login or a block, say so. Do not report that part as missing or as present.
11Cite a source where the fact it supports matters. Do not add a separate list of every source you used.
- 3
Source hierarchy
SharedEncourages the AI to use the most reliable explanation available instead of casually relying on marketing blogs or unsupported opinion.
source-hierarchy1Prefer references in this order:
21. Official provider or platform documentation where the subject relates to a specific service or product.
32. A recognised neutral reference such as Wikipedia for general concepts.
43. Another authoritative source only when the first two are not suitable.
- 4
Two customer perspectives
Checks both people who already know the business name and people who are simply searching for a product or service.
perspectives1Consider someone searching specifically for [BUSINESS NAME].
2Also consider someone who does not know the business exists and is searching for its products or services in [LOCATION].
- 5
Can I find the business?
Looks at whether a customer can discover the business by name, by service, or through ordinary local searches.
findability1Search for [BUSINESS NAME].
2Search for [MAIN PRODUCTS / SERVICES].
3Search common ways a customer might describe those products or services in their own words.
4Search for the business name, then for two or three ways a customer would describe what it sells, with and without the location. Do not search the business-type label itself.
5Describe what you found rather than claiming everyone will see the same search results.
- 6
Does the business look credible?
Looks for the basic information and trust signals that help a customer feel confident the business is real, current and contactable.
credibility1Check the business name and description, location, contact details, opening hours where relevant, recent activity, reviews, consistency of information, useful photographs and other evidence that the business is active.
- 7
Is it immediately clear what the business does?
Tests whether somebody encountering the business for the first time can quickly understand the offer and what to do next.
clarity1Assess whether a new customer can quickly understand what the business offers, who it is for, where it operates, how to contact or visit it, how to book or buy where relevant, and why someone might choose it.
- 8
Is the information consistent?
Checks whether customers are being shown conflicting opening hours, phone numbers, addresses, services or other information in different places.
consistency1Check for obvious contradictions or outdated information across the website and other links I gave, if any, search results, directories and any social profiles you find. If my details turn out to be wrong, for example a website exists that I did not give, say so once and review what actually exists; do not make the correction a finding.
2Where a contradiction is found, show the sources containing the different information.
- 9
What does the customer experience look like?
Follows the simple path from needing something to taking action, looking for places where the customer may become confused or give up.
customer-journey1Follow the likely path: need something → search → discover → understand → trust → contact / visit / book / buy.
2Identify obvious points where that journey becomes confusing, difficult or stops.
- 10
Are there obvious missed opportunities?
Surfaces only reasonably clear opportunities at this stage instead of producing a huge marketing wish list.
missed-opportunities1Look for clear opportunities such as no website, a missing or weak Google Business presence, difficulty finding the business by service, unclear contact information, no obvious booking or enquiry route, abandoned useful social profiles, or important information customers have to hunt for.
2Do not turn this into a detailed specialist audit.
- 11
Finding format
SharedGives every finding the same useful structure. The reader sees what is already working, what may need attention, the evidence, why it matters and exactly what can be done next.
positive-finding-format1Report each finding using these headings, in this order:
2- Finding: A short plain-English description of the issue or opportunity.
3- Status: Shows whether the finding was directly observed, reasonably inferred, or could not be fully verified.
4- What is working: Recognises useful things already in place so the review stays balanced. Leave this out if nothing genuine applies; never invent a positive.
5- What may need attention: States the issue clearly and proportionately in plain English.
6- Evidence: Shows the page, profile, search result, listing or other source supporting the finding.
7- Why this matters: Connects the finding to a real customer or business consequence.
8- How to put it right: Provides a practical step-by-step route to improvement rather than vague advice.
9- References for the fix: Reliable guidance you actually opened that supports the fix. Leave this out if no reference adds anything.
10- Effort: Exactly one of Small, Moderate or Larger, giving a rough sense of the work involved without inventing precise cost or time estimates.
- 12
Recommendation discipline
SharedPrevents the AI from defaulting to rebuilds, subscriptions or fashionable tools when a smaller change would solve the problem.
recommendation-discipline1Prefer simple, realistic improvements over large projects.
2Fix or improve what already exists before recommending replacement.
3Do not recommend a paid product, subscription, redesign, rebuild or new platform simply because one exists.
4Keep recommendations proportionate to the business and the evidence found.
5Do not create an exhaustive improvement list when a smaller set of meaningful actions will do.
- 13
Shape of the report
SharedLong reports go unread. This keeps the answer to a length a busy owner will actually read, and stops the AI printing its own instructions as headings.
report-shape1Sections such as Language and tone, Evidence and certainty, Source hierarchy, Recommendation discipline, Research boundaries and Limits of this particular prompt are instructions for you, not headings for the report.
2Keep the whole report to about a seven-minute read, unless this prompt says otherwise. Make each point once and refer back to it rather than repeating it under later headings. Put minor points in one short list.
3Cover every section this prompt asks for, even briefly. If a section has nothing useful to add, say so in a line rather than filling it.
- 14
How the results should be presented
Makes the report easy to read and act on, with a short first impression, positive findings, structured issues, priorities and anything that could not be confirmed.
output1Present the results under these headings, in this order:
21. First impression
32. What appears to be working
43. Things worth looking at, each using the finding format above
54. Three useful actions
65. What I could not verify
76. Something useful I learned
- 15
Action prioritisation
SharedTurns a long analysis into a small number of useful next steps. You should finish knowing what to do first, not merely knowing what is wrong.
action-prioritisation1Finish with the three actions most worth considering first, drawn from the findings or ideas above.
2For each action include what to do, why it comes first and the first practical step, referring to the finding it comes from rather than repeating it. Add a reference only if you opened one that genuinely helps with that step.
3Prefer small, realistic improvements where they can produce a meaningful result.
- 16
Something useful I learned
SharedAdds the quiet educational layer. Instead of delivering a lecture, the prompt explains one useful marketing, customer-experience or technology concept that arose naturally from the work.
teaching-note1Briefly explain one marketing, customer-experience or technology concept that arose naturally from this review.
2Explain what it means and why it matters to this particular business, and, if you opened one, give a reliable place to learn more.
3Keep this short and practical.
4Do not turn the report into a lesson.
- 17
Research boundaries
SharedDefines what the AI must not do. It keeps a broad review from quietly becoming security testing, legal advice, invasive research or an unrelated technical audit.
research-boundaries1Stay within the stated purpose of this prompt.
2If something deserves deeper investigation, identify it, explain why it may matter, and recommend the appropriate deeper review instead of attempting that entire review here.
3Do not perform vulnerability scanning, penetration testing, endpoint probing, login attempts or other security testing.
4Do not submit forms, make bookings, place orders, contact the business or change anything.
5Do not claim legal or regulatory compliance or non-compliance from a broad review.
6Do not guess private information such as revenue, profitability, customer numbers, budgets, internal systems, staffing or business plans.
7Do not infer motives, competence or intentions of owners, staff, agencies or competitors.
- 18
Limits of this particular prompt
The boundaries that apply to this prompt specifically, on top of the general research limits.
scope-notes1This is a sanity check, not a detailed technical audit.
2Base findings on what a customer sees. Do not inspect page code or report technical search-engine, accessibility, performance or hosting findings; list any you suspect under What I could not verify.
3Finding a possible problem is not the same as fully diagnosing it.
SharedSections marked shared are word for word the same in every prompt that uses them. The rules on tone, evidence, recommendations and limits are deliberately identical wherever you meet them, so you only have to learn them once, and no prompt can quietly hold itself to a lower standard than the others.
What it deliberately will not do
- This is a sanity check, not a detailed technical audit.
- Base findings on what a customer sees. Do not inspect page code or report technical search-engine, accessibility, performance or hosting findings; list any you suspect under What I could not verify.
- Finding a possible problem is not the same as fully diagnosing it.
Ready to use it?
Fill in your business details once and we will write them into the prompt, ready to copy or download.
Make this prompt yours