Convert traceable customer questions and friction into useful topics without overstating demand. 제공할 내용: Customer feedback, Content strategy and product facts, Evidence and production constraints. 예상 결과: A source-linked topic backlog with audience need, evidence strength, format, risks, and validation.
1
맥락 추가
텍스트는 이 브라우저에 유지됩니다. AILesson Prompts는 이를 모델이나 서버로 보내지 않습니다.
2
프롬프트
채워지지 않은 필드는 플레이스홀더로 표시되므로 프롬프트를 복사하고 편집할 수 있습니다
Turn the supplied customer feedback into content-topic opportunities. Do not treat feedback as representative market research unless sampling supports it.
Anonymous feedback IDs, channels, dates, permitted segments, questions, context, and outcomes:
[feedback]
Audiences, journey, verified facts, exclusions, existing content, goals, voice, and authority:
[strategy]
Coverage, privacy, consent, recency, language, channels, capacity, SEO evidence, approval, and review:
[constraints]
Preserve every feedback ID. Separate direct question, observed friction, requested feature, objection, praise, misconception, workaround, and content hypothesis. Remove personal/sensitive details and do not quote publicly without permission. Cluster by underlying job or decision, not shared words; retain contradictory and minority feedback. Report counts with denominators and channel/time coverage, while noting repeat customers or self-selection. Do not infer search volume, prevalence, intent, or product capability.
For each topic provide audience/job, source IDs, evidence strength and bias, question to answer, factual boundary, content angle, journey stage, format/channel rationale, CTA, existing-content gap, required expert/source, privacy/brand risk, effort, reuse, success signal, and validation step. Distinguish answerable education from product/support issue that content cannot solve. Prioritize only with supplied criteria; otherwise create conditional tiers. End with rejected/merged topics, missing perspectives, a source-to-topic ledger, and questions needing product, legal, support, or SEO confirmation.
기본적으로 비공개프롬프트 구성은 브라우저에서 로컬로 이루어집니다. 조직에서 허용하지 않는 한 기밀 정보를 AI 서비스에 입력하지 마세요.
입력에서 결과까지
적용 예시
구체적인 맥락이 이 레시피를 바로 사용할 수 있는 결과로 바꾸는 방법을 확인하세요
실제 입력
Customer feedback
30 anonymized support contacts, 1-21 Aug 2026, all inbound after workshop-page visits; unique-contact dedup applied. F01-F08 ask whether laptops are provided. F09-F13 ask if beginners can attend. F14-F17 ask about Chinese interpretation. F18-F20 say session times conflict with work. F21-F23 request recordings. F24 says the page was clear; F25-F26 praise staff replies. F27-F28 think the workshop teaches job-search skills. F29 cannot complete the registration form with keyboard only; F30 asks whether data entered in practice is stored. Outcomes: staff answered manually; F29 escalated to accessibility owner. No public-quote consent. No demographic data.
Content strategy and product facts
Actual offer: free in-person workshop on using online public services; English with Chinese interpretation; beginners may attend; library laptops are available but limited and must be reserved; no recording; not job-search training. Practice uses fictional data; registration form privacy notice is owned by privacy team. Existing page lists dates/language but omits device reservation, beginner level, fictional practice data, and explicit non-job-search scope. Goal: reduce avoidable pre-registration uncertainty, not suppress support contact. CTA is view sessions/register or contact support.
Evidence and production constraints
Feedback covers only support contacts after page visits, not all visitors; 30 unique contacts, self-selected. No SEO volume data. Web article and FAQ capacity: two pieces this month; bilingual review available. Product/accessibility fixes outrank content when blocking. Privacy/accessibility claims need owner approval. Review 30 Sep 2026.
예시 출력
Coverage: all F01-F30 retained; counts are among 30 self-selected support contacts, not visitor prevalence. No quotes may be published.
Tier 1 content candidate—“Before you register: level, laptops, language, and what the workshop covers.” Sources F01-F17/F27-F28: 19 contacts across four decisions, with one positive-clear counterexample F24. Answer boundaries: beginners allowed; limited laptops by reservation; English + Chinese interpretation; online public services, not job search. Format: bilingual page section + FAQ, because information belongs at decision point. CTA view sessions/register; success signal fewer contacts on these exact coded questions per page visitor only if visitor denominator becomes available, plus comprehension check. Product/content owner must confirm laptop reservation workflow.
Tier 2 candidate—“What happens to information used in workshop practice?” F30 only, weak-frequency but high trust relevance. State only fictional practice data; registration privacy is separate and needs privacy-owner wording. Merge as a short FAQ within piece one rather than infer broad demand. F21-F23 recording requests cannot be answered with a how-to because no recording exists; page should accurately say in-person/no recording, while program owner separately assesses access alternatives. F18-F20 timing conflict is an offer/scheduling issue, not solvable by explanatory content.
Critical non-content item: F29 keyboard blockage is a product accessibility defect. Keep escalated; do not publish a workaround as substitute. It gates promotion until owner verifies form access. Praise F25-F26 is feedback, not a topic; F24 is a useful counterexample.
Two-piece capacity: (1) update landing-page decision block/FAQ covering level, devices, language, scope, practice data after approvals; (2) a reusable “What to expect” article only if it adds step-by-step arrival/device-reservation information from verified operations sources. No SEO claim without keyword data. Ledger: T1←F01-F17,F27-F28,F24; privacy FAQ←F30; program decision←F18-F23; accessibility fix←F29; no topic←F25-F26. Review codes and page/support denominators on 30 Sep.
효과가 있는 이유
1
Source-linked clusters preserve the difference between repeated evidence and one memorable anecdote
2
Separating content gaps from product defects prevents publishing an explanation where the experience needs repair
결과 확인
Is every topic linked to feedback IDs with counts, coverage, bias, and contradictory evidence
Are factual boundaries and required expert sources explicit before drafting
Are content opportunities separated from issues requiring product, policy, or support action
안심하고 사용하세요
자주 묻는 질문
이 레시피를 언제 사용해야 하는지, 무엇을 제공해야 하는지, 그리고 어떤 부분에서 사람의 검토가 여전히 중요한지에 대한 실용적인 답변
What should I prepare before using “Turn customer feedback into content topic opportunities”?
For “Turn customer feedback into content topic opportunities,” prepare Customer feedback, Content strategy and product facts, and Evidence and production constraints. Replace placeholders only with information you can verify. If a detail is unknown, preserve that uncertainty explicitly instead of asking the model to infer it.
When is the “Turn customer feedback into content topic opportunities” result not ready to use?
The result is not ready if it does not yet deliver the stated outcome—A source-linked topic backlog with audience need, evidence strength, format, risks, and validation—from the supplied evidence, or if it relies on unresolved assumptions, missing approvals, or invented details. Use the checks as release gates: revise the source inputs or assign a named, authorized reviewer instead of polishing an unsupported output.
Which AI tools have recorded tests for “Turn customer feedback into content topic opportunities”?
The published test record for “Turn customer feedback into content topic opportunities” lists ChatGPT as of 2026-08-28. This confirms recorded runs, not guaranteed compatibility or identical results in later product versions. For another tool or version, keep every constraint visible and repeat the result checks before use.
ChatGPT
