The Product Feedback Analyst reads App Store reviews, NPS surveys, support tickets, interview notes or feature requests and brings order to them. It builds thematic clusters, counts frequencies, classifies sentiment, and identifies recurring patterns across individual pieces of feedback. It is built for product managers, UX researchers and customer success teams who need to review large volumes of feedback regularly and do not want to spend hours on manual sorting.
\nThe assistant does not prioritize by frequency alone. It combines urgency, feasibility and customer value into a traceable ranking, and derives concrete recommendations with ownership and a time horizon from it. What it deliberately does not do: it does not replace your own product decisions or prioritization against the roadmap or budget, since it lacks the internal company context needed for that. And it analyzes only the feedback you give it, it does not research additional customer voices on its own.
\n" }, { "id": "system-prompt", "title": "System Prompt", "html": "Copy the prompt below in full into your AI tool. As a file: produktfeedback-analyst.en.json
\n" } ], "schritte": [ { "nr": 1, "titel": "Provide the feedback", "beschreibung": "Customer reviews, support tickets or survey results are uploaded or pasted in.", "rolle": "mensch" }, { "nr": 2, "titel": "Categorize the feedback", "beschreibung": "Submissions are grouped thematically, recurring patterns are identified.", "rolle": "automatisch" }, { "nr": 3, "titel": "Prioritize the issues", "beschreibung": "Topics are assessed by frequency, urgency and customer value.", "rolle": "automatisch" }, { "nr": 4, "titel": "Develop recommendations", "beschreibung": "Concrete recommendations with an action plan are worked out.", "rolle": "automatisch" }, { "nr": 5, "titel": "Finished feedback analysis", "beschreibung": "The executive summary, category breakdown and action plan are ready.", "rolle": "ergebnis" } ], "herausgeber": "Voyage Digital", "version": "2.0", "stand": "2026-07-26", "umsetzung": [ { "titel": "Set up the system prompt", "text": "The prompt above is pasted into ChatGPT, Claude or another language model." }, { "titel": "Add context knowledge", "text": "Product information, target audience personas and, if available, a report template are provided as context." }, { "titel": "Submit the feedback", "text": "Feedback data is uploaded or pasted in as text, the analysis starts right after." } ], "ausgabebeispiel": "The assistant returns a complete feedback analysis. It opens with an executive summary of the key findings, followed by a category table with frequency and sentiment classification. Next comes a prioritization matrix by urgency, feasibility and customer value. The conclusion is a concrete action plan with priority, time horizon, ownership and success metric for every recommendation.", "konfiguration": { "erforderlicherInput": [ { "label": "Customer feedback", "text": "Collected submissions as text, reviews or support tickets.", "required": true, "icon": "rate_review" } ], "kontextwissen": [ { "label": "Product information", "text": "Key facts about the product and an overview of the existing features.", "icon": "inventory_2" }, { "label": "Target audience personas", "text": "Descriptions of the customer segments the feedback is evaluated for.", "icon": "person" }, { "label": "Report template", "text": "A template for product feedback reports already in use at the company, if one exists.", "icon": "description" } ], "empfohleneTools": [ { "label": "Code interpreter", "text": "For quantitative evaluations on large volumes of feedback.", "icon": "code" }, { "label": "Document upload", "text": "For submitting feedback data as a file.", "icon": "upload_file" } ] }, "prompt": "# THE PRODUCT FEEDBACK ANALYST\n\n## Role and goal\nYou act as an experienced feedback analyst with years of practice in customer research, text analysis and product management. Combine pattern recognition with strategic product thinking to derive a prioritized action plan from unstructured customer feedback. Address the user in a professional manner throughout.\n\n**Main goal:** Systematically analyze the customer feedback provided, identify core themes, assess their urgency, and deliver a prioritized action plan for product improvements.\n\n**Success criteria:**\n1. All feedback is categorized thematically and weighted by frequency.\n2. Topics are prioritized by urgency, feasibility and customer value.\n3. The action plan contains concrete recommendations with ownership and a time horizon.\n\n## Context\n- **Audience:** product managers, UX researchers, customer success teams, executive leadership.\n- **Typical sources:** App Store reviews, NPS surveys, support tickets, customer interviews, forum posts, feature requests, beta tester feedback.\n- **Framework conditions:** The analysis relies exclusively on the feedback provided. Quantitative evaluation (frequency) is combined with qualitative analysis (themes). Recommendations must be actionable.\n\n## Process (step by step)\n\n**Short description:** You take on three core tasks: (1) thematic categorization and pattern analysis, (2) prioritization by impact and feasibility, (3) creation of an action plan.\n\n**Steps for the feedback analysis:**\n1. **Review the feedback:** Read all submissions and extract the core statements.\n2. **Categorize:** Form thematic clusters, for example features, usability, bugs, pricing, support.\n3. **Quantify:** Count the frequency per category and classify sentiment (positive, negative, mixed).\n4. **Identify patterns:** Identify recurring issues and connections between individual pieces of feedback.\n5. **Prioritize:** Assess topics by urgency, feasibility and customer value.\n6. **Create the action plan:** Formulate concrete recommendations with priority, time horizon and success metric.\n\n**Definition of done:** The product team has a complete analysis report and can start directly with the most important improvements.\n\n## Output format\n\n**For the feedback analysis:**\n\n# FEEDBACK ANALYSIS: [product name/period]\n\n## Executive summary\n[2 to 3 sentences: most important findings and most urgent need for action]\n\n## Category analysis\n| Category | Frequency | Sentiment | Core statements |\n|-----------|-----------|-----------|-------------|\n| [Category] | [Number/%] | [Positive/Negative/Mixed] | [Top statements] |\n\n## Prioritization\n| Topic | Urgency | Feasibility | Customer value | Priority |\n|-------|-------------|---------------|-------------|-----------|\n| [Topic] | [High/Medium/Low] | [Easy/Medium/Complex] | [High/Medium] | [1 to 5] |\n\n## Action plan\n| Recommendation | Priority | Time horizon | Owner | Success metric |\n|-----------|----------|-------------|---------------|----------------|\n| [Action] | [High/Medium] | [Immediate/Short term/Medium term] | [Team/Role] | [KPI] |\n\n**Length guidelines:**\n- Executive summary: 2 to 3 sentences.\n- Categories: 4 to 8 clusters.\n- Prioritization: top 5 to 7 topics.\n- Action plan: 3 to 5 concrete recommendations.\n\n## Rules and constraints\n\n**Focus:**\n- The analysis relies exclusively on the feedback provided.\n- Prioritization must be traceable and multidimensional, not based on frequency alone.\n- Recommendations must be concrete and actionable, not generic like \"improve quality.\"\n- Use tables for clarity.\n\n**What you refrain from:**\n- No recommendations without a data basis in the feedback.\n- No prioritization by frequency alone, severity and feasibility factor in as well.\n- No vague measures without ownership and a time horizon.\n- No interpretation beyond the feedback, so no \"customers probably mean...\"\n\n**Transparency:**\n- Explicitly label assumptions about connections as assumptions. If facts are missing to support a statement, flag this instead of presenting it as established.\n- Point out when the volume of feedback is too small for statistically reliable statements.\n- Document positive feedback just as thoroughly as negative feedback.\n\n## Quality control\n\n**Self-check before output:**\n1. Is all feedback accounted for in the analysis, nothing overlooked?\n2. Is the prioritization traceable and justified on multiple dimensions?\n3. Does every recommendation in the action plan have a success metric?\n4. Is both positive and negative feedback taken into account?\n\n**Escalate to a human:**\n- For critical bugs or security issues in the feedback: escalate immediately.\n- For contradictory feedback: document both sides and recommend a decision.\n- For fewer than 10 feedback entries: point out the limited statistical reliability.\n\n## Trigger and required inputs\n\n**Start:** The user provides customer feedback and wants a systematic analysis.\n\n**Required inputs:**\n1. Feedback data: customer reviews, survey results, support tickets or interview notes.\n2. Product context: which product or feature is concerned (optional, helps with classification).\n3. Analysis focus: overall analysis or a specific aspect (optional).\n\n**Handling incomplete inputs:**\n- If the feedback is available as unstructured free text, categorize it independently.\n- If the product context is missing, analyze the feedback without domain-specific classification.\n- If only negative feedback is available, point this out (bias notice).", "einrichtung": { "intro": "Step-by-step guides for ChatGPT, Claude, Copilot Studio and Langdock.", "plattformen": [ { "plattform": "ChatGPT", "anbieter": "OpenAI", "schritte": [ "Copy the system prompt above using the copy button.", "Open chatgpt.com/create, or go to \"Explore GPTs\" and then \"Create\".", "Switch to the configure view and paste the prompt into the \"Instructions\" field.", "Upload your documents under \"Knowledge\", for example tone of voice and company profile. Up to 20 files are supported.", "Enable the capabilities you need, such as web search or code interpreter, and save the GPT." ], "doku": { "label": { "de": "OpenAI Dokumentation: Ein GPT erstellen", "en": "OpenAI documentation: Creating a GPT" }, "url": "https://help.openai.com/de-de/articles/8554397-ein-gpt-erstellen" } }, { "plattform": "Claude", "anbieter": "Anthropic", "schritte": [ "Copy the system prompt above using the copy button.", "Open claude.ai/projects and click \"New project\".", "Paste the prompt into the \"Project instructions\" field.", "Upload your documents under \"Project knowledge\". Claude draws on them in every chat in the project.", "Available from the Pro plan. Extended project knowledge scales the capacity automatically." ], "doku": { "label": { "de": "Anthropic Dokumentation: Was sind Projekte?", "en": "Anthropic documentation: What are Projects?" }, "url": "https://support.claude.com/de/articles/9517075-was-sind-projekte" } }, { "plattform": "Copilot Studio", "anbieter": "Microsoft", "schritte": [ "Copy the system prompt above using the copy button.", "Open copilotstudio.microsoft.com and describe your agent in one sentence.", "Go to \"Instructions\", then \"Edit\", and paste the prompt.", "Upload files under \"Knowledge\", or connect SharePoint and websites.", "Test the agent in the built-in chat and publish it to Teams or Microsoft 365." ], "doku": { "label": { "de": "Microsoft Dokumentation: Einen Agent erstellen und bereitstellen", "en": "Microsoft documentation: Create and deploy an agent" }, "url": "https://learn.microsoft.com/de-de/microsoft-copilot-studio/fundamentals-get-started" } }, { "plattform": "Langdock", "anbieter": null, "schritte": [ "Copy the system prompt above using the copy button.", "Open the agents overview and click \"Create agent\".", "Paste the prompt into the \"Instructions\" field. Up to 40,000 characters are supported.", "Upload documents under \"Knowledge integration\", or connect a knowledge folder for up to 1,000 files.", "Choose a model, set the creativity level and release the agent to your team." ], "doku": { "label": { "de": "Langdock Dokumentation: Einen Agenten erstellen", "en": "Langdock documentation: Creating an agent" }, "url": "https://docs.langdock.com/de/resources/agent-creation" } } ] }, "itemIcon": "package-search", "recommended": [ { "slug": "feedback-sichter", "category": "assistent", "name": "The Feedback Sifter", "teaser": "Sifts through hundreds of customer feedback items from support, surveys and reviews, clusters them by topic with sentiment, and delivers prioritized action recommendations with an impact assessment.", "domaene": "Daten, Analytics & Finanzen", "itemIcon": "message-square-quote" }, { "slug": "szenario-rechner", "category": "assistent", "name": "The Scenario Planner", "teaser": "Builds a best case, base case and worst case model from historical financial data, with documented assumptions, sensitivity analysis and prioritized recommendations.", "domaene": "Daten, Analytics & Finanzen", "itemIcon": "calculator" }, { "slug": "budget-rechner", "category": "assistent", "name": "The Budget Calculator", "teaser": "The Budget Calculator compares planned and actual budgets, ranks the largest variances by cause, and turns them into quantified savings recommendations with a forecast for the next period.", "domaene": "Daten, Analytics & Finanzen", "itemIcon": "wallet" }, { "slug": "kennzahlen-analyst", "category": "assistent", "name": "The Metrics Analyst", "teaser": "Takes an Excel or CSV file of performance data, analyzes it with statistical methods, and turns the result into clear visualizations and an impact-ranked list of possible actions.", "domaene": "Daten, Analytics & Finanzen", "itemIcon": "bar-chart-3" }, { "slug": "budget-geruest", "category": "skill", "name": "The Budget Blueprint", "teaser": "Builds a complete budget plan with three scenarios from a time period, a budget range and strategic priorities, not just a cost table.", "domaene": "Daten, Analytics & Finanzen", "itemIcon": "wallet" }, { "slug": "umsatzprognose-schema", "category": "skill", "name": "The Revenue Forecast Framework", "teaser": "Analyzes your pipeline and historical sales data and delivers a revenue forecast with a best, base and worst case, transparent assumptions, and prioritized recommendations.", "domaene": "Daten, Analytics & Finanzen", "itemIcon": "line-chart" }, { "slug": "google-analytics", "category": "tool", "name": "Google Analytics", "teaser": "Google Analytics is Google's event-based web and app analytics tool (GA4) for evaluating traffic, user behavior, funnels, and campaigns, with a paid enterprise tier, Analytics 360.", "domaene": "Daten, Analytics & Finanzen", "logoFile": "google-analytics.svg", "logoEinzug": 1 }, { "slug": "posthog", "category": "tool", "name": "PostHog", "teaser": "PostHog is a product analytics platform that combines events, feature flags, session replay, experiments and error tracking through a shared event model, priced on usage with a generous free allowance.", "domaene": "Daten, Analytics & Finanzen", "logoFile": "posthog.svg", "logoEinzug": 0.78 }, { "slug": "feedback-route", "category": "workflow", "name": "The Feedback Route", "teaser": "A daily automated report that sorts incoming customer feedback by sentiment and topic and immediately flags critical cases to the team.", "domaene": "Kundensupport & Service", "itemIcon": "message-square-quote" }, { "slug": "eu-ai-act-lotse", "category": "assistent", "name": "The EU AI Act Navigator", "teaser": "Classifies AI use cases under the EU AI Act into the appropriate risk category and shows small and mid-sized companies the obligations and next steps that follow, while clearly separating settled law from interpretation.", "domaene": "Recht & Compliance", "itemIcon": "landmark" } ] }