What are the use cases for this prompt?

This prompt can be used for: Analyze User Feedback.

What is the difficulty level and which AI tool should I use?

This prompt is intermediate level. It works with all AI tools (ChatGPT, Claude, Gemini, etc.).

Are there variants of this prompt?

Yes, 3 variants are available: Beginner, Intermediate, Advanced.

📊Analyse de donnéesIntermediateAll AIs

Perplexity Prompt for Analyzing User Feedback

Analyzing user feedback is a strategic lever for improving a product, service, or customer experience. Yet, faced with hundreds or even thousands of scattered reviews—Google reviews, social media comments, support tickets, and NPS surveys—the task quickly becomes time-consuming. Perplexity, with its augmented search and intelligent synthesis capabilities, can turn this mass of qualitative data into actionable insights. Unlike manual analysis that would take hours, Perplexity can cross-reference sources, identify recurring trends, and categorize feedback by theme in minutes. Whether you're a product manager prioritizing your roadmap, a CX manager looking to reduce churn, or a startup founder validating a pivot, a well-structured prompt transforms Perplexity into a true quality analyst. This guide offers an optimized prompt to extract maximum value from your user feedback, with variants adapted to your expertise level and need complexity.

Paste in your AI

Paste this prompt in ChatGPT, Claude or Gemini and customize the variables in brackets.

Act as a senior UX Research analyst specializing in Voice of Customer. I will provide you with a set of user feedback for [PRODUCT_SERVICE_NAME]. Analyze these comments using the following methodology:

Thematic categorization: Classify each feedback into a category (UX/UI, Performance, Features, Support, Pricing, Onboarding, Other). A feedback can belong to multiple categories.
Sentiment analysis: For each category, evaluate the overall sentiment (positive, neutral, negative) and assign a score from -5 to +5.
Pattern identification: Identify the 5 most recurring themes, with the number of occurrences and representative verbatim quotes.
Impact/frequency matrix: Classify the identified issues according to their frequency (how many users mention the problem) and perceived impact (severity of the problem for the user).
Prioritized recommendations: Propose an action plan in 3 horizons (quick wins within 2 weeks, medium-term improvements within 3 months, structural projects within 6 months).
Weak signals: Identify isolated but potentially critical feedback that warrants further investigation.

Here are the feedbacks to analyze:
[PASTE_FEEDBACKS_HERE]

Output format: structured table for each section, with a 5-line executive summary at the beginning.

Personalize this prompt with Léa

Léa rewrites this prompt for your job and your exact goal — 3 quick questions.

Why this prompt works

This prompt works by assigning an expert role (UX Research analyst) that anchors Perplexity in a precise methodological framework. The 6-step sequential structure forces exhaustive analysis rather than a superficial summary. The request for verbatim quotes and numerical scores forces the model to rely on actual data rather than generalize.

Use Cases

Analyze User Feedback

Variants

Expected Output

You will get a structured analysis report including an overview of user sentiment, a complete categorization of feedback with scores, and a visual priority matrix. The deliverable includes concrete recommendations classified by time horizon, directly usable to feed a product roadmap or a CX improvement plan.

Frequently Asked Questions

How many feedback items can I analyze in a single Perplexity query?

Perplexity accepts long prompts, but for optimal analysis, limit yourself to 100–150 feedback items per query. Beyond that, analysis quality declines as the model may skim over some entries. For larger volumes, split by source (Google reviews, support tickets, NPS) or by time period, then request a cross-synthesis in a separate query. Tip: number your feedback items so you can verify that each has been accounted for in the analysis.

Can Perplexity analyze feedback in multiple languages at once?

Yes, Perplexity handles multilingual analysis very well. You can submit feedback in French, English, Spanish, or other languages within the same query. Simply specify your desired output language in the prompt. Note, however, that sentiment analysis is slightly more reliable on English-language feedback. For other languages, add an instruction like "Take into account cultural nuances in how dissatisfaction is expressed" to avoid false positives or negatives.

How can I supplement Perplexity's analysis with existing quantitative data?

Integrate your metrics directly into the prompt to enrich the analysis. For example, add your current NPS score, churn rate by segment, or product usage data. Perplexity can then correlate qualitative feedback with your KPIs. Phrase it like this: "Data context: Overall NPS 32, monthly churn 8%, feature X used by 23% of active users." The model naturally weights its recommendations based on this data, making the action plan more realistic and aligned with your business priorities.

Improve this prompt

Run this prompt through the Optimizer to strengthen its context, constraints and expected format.

Improve this prompt with the Optimizer

Comments

LéaAI
Pour exploiter pleinement ce prompt sur Perplexity, précisez le canal d'origine des feedbacks (tickets support, avis store, interviews…). Cela affine la catégorisation et pondère l'analyse de sentiment. Ajoutez aussi une demande de sortie en JSON pour récupérer les résultats dans un outil de data-viz ou un tableau de bord.