Critique your competitor’s website. Then yours.
A competitor’s website can make your own site easier to see. Start with real customer needs, inspect both sites against the same questions, and turn the comparison into usable improvements.
Try it now
Copy the prompt into your AI tool of choice, then answer its questions as they come.
Paste it into any AI chat to start. For most people, this is all you need.
Everything on this page in one paste: the prompt plus the full plan, every step and what to check. Use it for longer moves, to plan ahead, to share with a colleague, or if your AI can't open links.
How it goes
What the AI will do
- Investigates customer tasks and objections, then inspects the competitor’s actual website and yours.
- Tests important customer journeys and produces specific, checked copy and design improvements.
What to have ready
- Your website and a competitor’s, or enough information to identify them.
- Any particular customer, offer, or site objective you want examined.
Where you come in
- Settle a material scope choice or confirm a proposed claim about your offer.
- Review the proposed improvements before any separate implementation.
What you'll get
You have a comparison based on the pages actually inspected, with customer evidence distinguished from provisional assumptions, plus checked replacement copy and concrete design recommendations for your site. Missing evidence and partial coverage are identified.
You're done when
You have a comparison based on the pages actually inspected, with customer evidence distinguished from provisional assumptions, plus checked replacement copy and concrete design recommendations for your site. Missing evidence and partial coverage are identified.
These are general instructions, not a description of this user's particular AI system, tools, access, or circumstances. Adapt the method to the user's goal and the capabilities you can actually use, while preserving the activity's essential sequence, review points, and intended result. ### Start with the activity and the user's context Read the complete activity and guide the user through it. Use the activity prompt yourself; the user does not need to paste it again. Keep the responsibilities of the user, the AI, and any colleague clear. Begin with what the user has already supplied. Establish the intended result and resolve missing context through focused questions when needed. Work within the activity's stated scope, permissions, required confirmations, and stopping points, including any deliberate order for introducing information. Make progress with the available information and reasonable, clearly identified assumptions where the activity allows them. ### Check the capabilities needed for this work Inspect relevant available tools, connectors, and data. Use small, relevant, non-destructive checks to establish whether necessary access or a capability actually works. Naming a product does not establish access to it. Let this activity determine what needs checking; do not impose a universal preliminary questionnaire or a full system audit. When useful access is missing: - Explain what you cannot reach and how that material would help. - Investigate practical setup, connection, export, or other access alternatives before asking the user to gather material or troubleshoot. - If progress depends on access, request only the specific user action or permission needed to enable it or provide the material another way. Continue useful independent work while awaiting the response. - Offer to walk the user through an export or upload. Welcome files, links, copied text, rough notes, or an interview as supported by your system and the activity, and use the best available route. If the missing access is optional, continue with what is available. ### Ask focused questions and respect the answers Ask questions only when necessary to complete the work well or satisfy the activity's required review points. Build on answers already supplied. Ask one question at a time, or a small group of closely related questions. Wait on work that depends on the answer, and continue useful work that does not. Explain unfamiliar language with examples where helpful. Confirm answers or decisions you supply on the user's behalf before treating them as the user's final answers or decisions. This does not require separate approval of every sourced finding; follow the activity's specific review requirements. ### Keep evidence and independent contributions distinct Distinguish evidence, inference, and missing information. Check your work against the source material. Use independent agents when your system actually supports delegation and independent investigation or review would improve the work: - Give each agent a bounded brief and the context appropriate to its role. - Keep discovery independent until synthesis where the activity requires it. Preserve any requirement for the user or colleagues to contribute before seeing other explanations. - Follow the activity's stated fallback and any required confirmation when independent agents or fresh contexts are unavailable. Preserve reviewer isolation where required; describe shared-context or sequential passes accurately. ### Produce, check, and revise the result Do the substantive investigation and production. Carry the activity through to the most complete, usable result within its scope, rather than ending with a plan or handing the main work back to the user. When missing information does not prevent useful work, proceed with clearly identified assumptions where the activity permits them. Check the result against the activity's completion criteria. At each substantive delivery, state what is complete and any material unfinished work, assumptions, helpful missing information, and remaining uncertainty. Explain how these affect what the user can use, and help the user revise the result. Preserve the activity's stopping point. Do not turn a rehearsal, investigation, or test-design activity into execution that the user has not authorized. ### Establish the two sites and the customer task Critique my competitor's website, then mine, and turn the comparison into specific improvements for my site. Start with the URLs or company names I supplied. Confirm which sites and offers are relevant through the available evidence. If there are several materially different markets or products, recommend a useful bounded comparison and ask me to settle the scope before dependent work. Inspect what browsing, rendering, and screenshot capabilities you actually have. Plan to inspect the live pages, not merely search snippets or a remembered brand impression. If a site is inaccessible, try a permitted public route or help me provide a usable capture. Record the inspection date and pages actually viewed. A partial capture supports a limited review; do not imply that unvisited journeys were tested. ### Find customers' actual questions Inspect and try relevant available connections. Search customer and sales emails, chats, call notes and transcripts, calendar-linked meetings, research documents, project records, and available CRM, support, or usage data. Look for customers' tasks, buying questions, objections, vocabulary, decision roles, and points where they seek reassurance or abandon a process. Use the current offer and customer segment to keep searches relevant. Distinguish documented customer behavior from salespeople's interpretations and your hypotheses. Keep sources and dates for consequential findings. If access is missing, investigate a connection or export route and help obtain a focused record. With no customer evidence, use a clearly provisional task model and ask for one consequential clarification where it changes the comparison. Do not declare what all customers want from your own aesthetic preferences. ### Set common criteria and inspect the competitor first Derive a concise set of evaluation questions from the evidence. Useful questions may include: - Can a relevant customer tell whether this offer fits? - Can they understand the outcome and important limits? - Can they find credible support and resolve a known objection? - Can they take the next sensible step? Choose criteria that fit this site, rather than applying a generic checklist to every company. Inspect the competitor first, following the main customer journeys through actual pages. Capture exact examples, page references, and relevant screenshots when available. Identify what the site communicates effectively, where it creates confusion, and what evidence supports each judgment. Distinguish a design observation from a claim about business performance. Public website quality alone does not establish conversion rates or product quality. ### Inspect my site using the same questions Apply the same customer tasks and criteria to my site. Inspect the corresponding pages and journeys rather than judging my homepage against the competitor's entire site. Note differences in offer, audience, or buying process that make a direct comparison misleading. Where useful, give separate agents bounded customer-perspective journeys with the actual pages, relevant source references, known concerns, and uncertainties. Keep initial findings independent before synthesis. Bound work by journey and page set, maintain coverage, and use successive waves for large sites. A lead should check cross-page coherence. Without agents, use manageable separate passes or fresh-session handoffs and disclose their actual independence. Do not submit forms, make purchases, create accounts, or contact sales as part of a browsing review. ### Produce improvements worth making Reconcile observations against customer evidence. Prioritize changes by the important task they improve, the strength of support, and dependencies. Avoid copying the competitor's claims or visual identity; use what the comparison revealed about clarity and customer need. Write complete replacement copy for the most consequential selected pages or sections. Specify layout changes concretely, using annotated captures or a clear section-by-section description where visual tools are unavailable. Connect each change to the problem observed and the evidence behind it. Check new claims against my actual offer and records. Ask me to decide before presenting an unestablished promise, price, service commitment, or positioning choice as approved. ### Check and deliver the package Review the proposed copy and layout from the customer perspectives again. Check whether the original question is now answered, whether the next action is clear, and whether a new contradiction appears. Deliver the comparison, inspected-page record, replacement copy, concrete design recommendations, and a concise priority order. Mark untested performance assumptions and any remaining access limits. Keep the result usable even if only text-based recommendations could be produced. Stop at this improvement package; do not change or publish either website. These instructions were written in September 2026 using the frontier models available at the time. You may now have better tools or models, or restrictions that make some tasks harder. Your AI should adapt to the tools and access you actually have and find the best available way to help. Everything here is a starting suggestion for you and your AI, not a proven best practice for every setup. Feel free to rewrite any of it to better meet your needs.
View full AI instructions
Critique your competitor’s website. Then yours.
What the AI will do
- Investigates customer tasks and objections, then inspects the competitor’s actual website and yours.
- Tests important customer journeys and produces specific, checked copy and design improvements.
What you can provide
- Your website and a competitor’s, or enough information to identify them.
- Any particular customer, offer, or site objective you want examined.
Where you'll take part
- Settle a material scope choice or confirm a proposed claim about your offer.
- Review the proposed improvements before any separate implementation.
What you'll get
You have a comparison based on the pages actually inspected, with customer evidence distinguished from provisional assumptions, plus checked replacement copy and concrete design recommendations for your site. Missing evidence and partial coverage are identified.
Activity context
A competitor’s website can make your own site easier to see. Start with real customer needs, inspect both sites against the same questions, and turn the comparison into usable improvements.
For the user
Provide the two websites and any particular concern. The AI will investigate how customers use the offer, inspect the competitor first and your site second, and prepare actual replacement copy and concrete design recommendations. This activity ends with the improvement package.
Guidance for the AI
These are general instructions, not a description of this user's particular AI system, tools, access, or circumstances. Adapt the method to the user's goal and the capabilities you can actually use, while preserving the activity's essential sequence, review points, and intended result.
Start with the activity and the user's context
Read the complete activity and guide the user through it. Use the activity prompt yourself; the user does not need to paste it again. Keep the responsibilities of the user, the AI, and any colleague clear.
Begin with what the user has already supplied. Establish the intended result and resolve missing context through focused questions when needed. Work within the activity's stated scope, permissions, required confirmations, and stopping points, including any deliberate order for introducing information. Make progress with the available information and reasonable, clearly identified assumptions where the activity allows them.
Check the capabilities needed for this work
Inspect relevant available tools, connectors, and data. Use small, relevant, non-destructive checks to establish whether necessary access or a capability actually works. Naming a product does not establish access to it. Let this activity determine what needs checking; do not impose a universal preliminary questionnaire or a full system audit.
When useful access is missing:
- Explain what you cannot reach and how that material would help.
- Investigate practical setup, connection, export, or other access alternatives before asking the user to gather material or troubleshoot.
- If progress depends on access, request only the specific user action or permission needed to enable it or provide the material another way. Continue useful independent work while awaiting the response.
- Offer to walk the user through an export or upload. Welcome files, links, copied text, rough notes, or an interview as supported by your system and the activity, and use the best available route. If the missing access is optional, continue with what is available.
Ask focused questions and respect the answers
Ask questions only when necessary to complete the work well or satisfy the activity's required review points. Build on answers already supplied. Ask one question at a time, or a small group of closely related questions. Wait on work that depends on the answer, and continue useful work that does not. Explain unfamiliar language with examples where helpful.
Confirm answers or decisions you supply on the user's behalf before treating them as the user's final answers or decisions. This does not require separate approval of every sourced finding; follow the activity's specific review requirements.
Keep evidence and independent contributions distinct
Distinguish evidence, inference, and missing information. Check your work against the source material.
Use independent agents when your system actually supports delegation and independent investigation or review would improve the work:
- Give each agent a bounded brief and the context appropriate to its role.
- Keep discovery independent until synthesis where the activity requires it. Preserve any requirement for the user or colleagues to contribute before seeing other explanations.
- Follow the activity's stated fallback and any required confirmation when independent agents or fresh contexts are unavailable. Preserve reviewer isolation where required; describe shared-context or sequential passes accurately.
Produce, check, and revise the result
Do the substantive investigation and production. Carry the activity through to the most complete, usable result within its scope, rather than ending with a plan or handing the main work back to the user. When missing information does not prevent useful work, proceed with clearly identified assumptions where the activity permits them.
Check the result against the activity's completion criteria. At each substantive delivery, state what is complete and any material unfinished work, assumptions, helpful missing information, and remaining uncertainty. Explain how these affect what the user can use, and help the user revise the result.
Preserve the activity's stopping point. Do not turn a rehearsal, investigation, or test-design activity into execution that the user has not authorized.
Your AI prompt
Establish the two sites and the customer task
Critique my competitor's website, then mine, and turn the comparison into specific improvements for my site. Start with the URLs or company names I supplied. Confirm which sites and offers are relevant through the available evidence. If there are several materially different markets or products, recommend a useful bounded comparison and ask me to settle the scope before dependent work.
Inspect what browsing, rendering, and screenshot capabilities you actually have. Plan to inspect the live pages, not merely search snippets or a remembered brand impression. If a site is inaccessible, try a permitted public route or help me provide a usable capture. Record the inspection date and pages actually viewed. A partial capture supports a limited review; do not imply that unvisited journeys were tested.
Find customers' actual questions
Inspect and try relevant available connections. Search customer and sales emails, chats, call notes and transcripts, calendar-linked meetings, research documents, project records, and available CRM, support, or usage data. Look for customers' tasks, buying questions, objections, vocabulary, decision roles, and points where they seek reassurance or abandon a process. Use the current offer and customer segment to keep searches relevant.
Distinguish documented customer behavior from salespeople's interpretations and your hypotheses. Keep sources and dates for consequential findings. If access is missing, investigate a connection or export route and help obtain a focused record. With no customer evidence, use a clearly provisional task model and ask for one consequential clarification where it changes the comparison. Do not declare what all customers want from your own aesthetic preferences.
Set common criteria and inspect the competitor first
Derive a concise set of evaluation questions from the evidence. Useful questions may include:
- Can a relevant customer tell whether this offer fits?
- Can they understand the outcome and important limits?
- Can they find credible support and resolve a known objection?
- Can they take the next sensible step?
Choose criteria that fit this site, rather than applying a generic checklist to every company.
Inspect the competitor first, following the main customer journeys through actual pages. Capture exact examples, page references, and relevant screenshots when available. Identify what the site communicates effectively, where it creates confusion, and what evidence supports each judgment. Distinguish a design observation from a claim about business performance. Public website quality alone does not establish conversion rates or product quality.
Inspect my site using the same questions
Apply the same customer tasks and criteria to my site. Inspect the corresponding pages and journeys rather than judging my homepage against the competitor's entire site. Note differences in offer, audience, or buying process that make a direct comparison misleading.
Where useful, give separate agents bounded customer-perspective journeys with the actual pages, relevant source references, known concerns, and uncertainties. Keep initial findings independent before synthesis. Bound work by journey and page set, maintain coverage, and use successive waves for large sites. A lead should check cross-page coherence. Without agents, use manageable separate passes or fresh-session handoffs and disclose their actual independence. Do not submit forms, make purchases, create accounts, or contact sales as part of a browsing review.
Produce improvements worth making
Reconcile observations against customer evidence. Prioritize changes by the important task they improve, the strength of support, and dependencies. Avoid copying the competitor's claims or visual identity; use what the comparison revealed about clarity and customer need.
Write complete replacement copy for the most consequential selected pages or sections. Specify layout changes concretely, using annotated captures or a clear section-by-section description where visual tools are unavailable. Connect each change to the problem observed and the evidence behind it. Check new claims against my actual offer and records. Ask me to decide before presenting an unestablished promise, price, service commitment, or positioning choice as approved.
Check and deliver the package
Review the proposed copy and layout from the customer perspectives again. Check whether the original question is now answered, whether the next action is clear, and whether a new contradiction appears. Deliver the comparison, inspected-page record, replacement copy, concrete design recommendations, and a concise priority order. Mark untested performance assumptions and any remaining access limits. Keep the result usable even if only text-based recommendations could be produced. Stop at this improvement package; do not change or publish either website.
Done when
You have a comparison based on the pages actually inspected, with customer evidence distinguished from provisional assumptions, plus checked replacement copy and concrete design recommendations for your site. Missing evidence and partial coverage are identified.
These instructions were written in September 2026 using the frontier models available at the time. You may now have better tools or models, or restrictions that make some tasks harder. Your AI should adapt to the tools and access you actually have and find the best available way to help. Everything here is a starting suggestion for you and your AI, not a proven best practice for every setup. Feel free to rewrite any of it to better meet your needs.
These instructions were written in September 2026 using the frontier models available at the time. You may now have better tools or models, or restrictions that make some tasks harder. Your AI should adapt to the tools and access you actually have and find the best available way to help. Everything here is a starting suggestion for you and your AI, not a proven best practice for every setup. Feel free to rewrite any of it to better meet your needs.