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

Mistral Prompt for Analyzing User Feedback

Analyzing user feedback is a strategic lever for any company looking to improve its products and services. With Mistral, the leading French language model, you can automate this analysis at scale while maintaining a remarkable finesse of interpretation. Whether your feedback comes from satisfaction surveys, online reviews, support tickets, or social media comments, Mistral excels at detecting sentiment, identifying recurring themes, and prioritizing pain points. Its native understanding of French allows it to grasp cultural nuances, sarcasm, and idiomatic expressions that other models might miss. By properly structuring your prompt, you transform hundreds of raw feedback items into actionable insights in seconds. This guide offers an optimized prompt to extract maximum value from your user feedback with Mistral, along with variants adapted to your level of expertise and the complexity of your data.

Paste in your AI

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

You are a senior UX analyst specialized in leveraging user feedback. I will provide you with a list of raw user feedbacks. For each batch of feedback, perform the following analysis:

Sentiment Analysis: Classify each feedback as Positive, Negative, Neutral, or Mixed, with a confidence score (0-100%).
Theme Extraction: Identify the main themes that emerge (UX/UI, performance, pricing, customer support, features, onboarding, etc.). Group the feedback by theme.
Critical Pain Point Detection: List the 5 most mentioned problems in order of frequency and emotional intensity.
Improvement Opportunities: For each identified pain point, propose a concrete and prioritized recommendation (impact vs. effort).
Key Verbatims: Extract the 3 most representative quotes (positive and negative).
Estimated NPS Score: Based on the overall tone of the feedback, estimate an NPS range.

Format your response as a structured table for each section. Be factual, precise, and actionable.

Here is the feedback to analyze:
[PASTE_YOUR_FEEDBACK_HERE]

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 uses role-playing (senior UX analyst) to activate a rigorous analytical register in Mistral. The six numbered steps force a systematic analysis and avoid superficial responses. The request for confidence scores and impact/effort prioritization pushes the model to produce quantified results directly usable by a product team.

Use Cases

Analyze User Feedback

Variants

Expected Output

You will get a structured report including a sentiment classification for each feedback, a thematic map of the feedback, a top 5 of pain points with prioritized recommendations, representative verbatims, and an NPS estimate. Everything is formatted in clear tables, ready to be shared with your product team or management.

Frequently Asked Questions

How many feedback items can I analyze in a single request with Mistral?

Mistral Large supports a 128K token context window, which allows you to analyze approximately 200 to 400 short feedback entries (1-2 sentences) in a single request. For larger volumes, split your feedback into batches of 100-200 and request a consolidated summary at the end. Tip: number your feedback items to make referencing easier during analysis.

Is Mistral reliable for detecting sarcasm and nuances in French?

Mistral, developed by a French team, offers some of the best French language understanding on the market. It correctly detects sarcasm in about 80-85% of cases, which is superior to most English-centric models. To improve detection, include an explicit instruction in your prompt like 'Pay attention to sarcasm, irony, and colloquial French expressions'. Ambiguous cases will be flagged with a lower confidence score.

How do I integrate this analysis into an automated workflow?

You can use the Mistral API (via La Plateforme) to automate the analysis. Connect your feedback source (Typeform, Zendesk, Google Sheets) to a Python script that calls the Mistral API with the optimized prompt, then store the results in a database or dashboard. Add the parameter response_format: {type: 'json_object'} in your API call to get results that are directly usable programmatically. No-code tools like Make or n8n also offer native Mistral integrations.

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
Pensez à fournir un contexte minimal (produit, version, période) avant la liste des feedbacks : Mistral affine ses analyses avec ces repères. Pour un traitement automatique, demandez une sortie en JSON structuré (sentiment, thème, confiance, recommandation) afin d’intégrer directement les résultats dans un tableau ou un outil de visualisation.