Mistral Prompt for Analyzing Customer Reviews

Mistral, the AI model developed by Mistral AI, excels in processing and analyzing textual data in French. Customer review analysis is a strategic lever for any company wanting to understand the perception of its products or services. Thanks to its nuanced understanding of natural language, Mistral can identify dominant sentiments, extract recurring themes, and detect weak signals in large volumes of customer feedback. Whether you manage e-commerce, SaaS, or B2B services, automating your review analysis saves hours of manual work while providing more accurate and structured insights. This prompt is designed to transform a raw corpus of reviews into an actionable analysis report with concrete recommendations ranked by priority. It works equally well with Google, Trustpilot, Amazon reviews, or any other customer feedback source.

The prompt

Mistral

You are an analyst specialized in customer experience and sentiment analysis. I will provide you with a set of customer reviews. Analyze them using this structured methodology:

Overall sentiment analysis: Classify each review as positive, neutral, or negative. Give the percentage distribution.
Recurring themes: Identify the 5 to 8 main themes mentioned (e.g., product quality, customer service, delivery, value for money, ease of use). For each theme, indicate the dominant sentiment and number of mentions.
Strengths: List the 3 elements most appreciated by customers, with representative exact quotes.
Pain points: List the 3 main sources of dissatisfaction, with exact quotes and a severity assessment (low / medium / critical).
Weak signals: Identify 2 to 3 emerging trends or isolated mentions that deserve attention.
Estimated NPS: Based on the tone and content of the reviews, estimate an indicative Net Promoter Score.
Actionable recommendations: Propose 5 concrete actions ranked by impact (high/medium) and effort (low/medium/high), in matrix form.

Output format: structured report with headings, bullet points, and Markdown tables.

Here are the reviews to analyze:
[PASTE YOUR REVIEWS HERE]

Personalize this prompt with Léa

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

Why it works

This prompt uses a methodical decomposition into 7 steps that forces the model to produce a comprehensive analysis rather than a superficial summary. The request for exact quotes anchors the analysis in real data and avoids hallucinations. The impact/effort matrix in the conclusion transforms the analysis into an action plan directly usable by product and marketing teams.

Expected result

You get a structured Markdown report including sentiment distribution in percentages, a table of recurring themes with frequency and tone, key positive and negative verbatims, and a matrix of 5 prioritized recommendations. The report is directly shareable with your teams and usable to guide product, customer service, or communication decisions.

Variants by level

FAQ

How many reviews can I analyze at once with Mistral?

The limit depends on the context window of the Mistral model used. Mistral Large supports up to 128K tokens, which is about 300 to 500 average-sized reviews in a single prompt. For larger volumes, split your reviews into batches of 200-300 and ask for a consolidated summary at the end. Tip: number your reviews to make it easier to reference citations in the analysis.

Can Mistral analyze reviews in multiple languages at the same time?

Yes, Mistral handles multilingualism very well, especially French, English, Spanish, German, and Italian. You can submit a mixed corpus and explicitly ask in your prompt that the analysis be returned in French. Simply specify: 'The reviews are in multiple languages, produce the entire analysis in French.' The model will automatically detect the language of each review.

How to get more reliable results on sentiment analysis?

To improve accuracy, add context to your prompt: specify your industry, the type of product or service involved, and your rating scale if applicable. For example, a 3-star out of 5 review in hospitality does not have the same meaning as in e-commerce. You can also ask Mistral to assign a confidence score (low/medium/high) to each sentiment classification to identify ambiguous reviews that require human review.

How to use this prompt

Copy the prompt with the button above.
Paste it into ChatGPT, Claude or your favorite AI assistant.
Replace the bracketed variables with your details, then refine the result.

About Prompt Guide

Prompt Guide is a free library of 4800+ ready-to-use prompts for ChatGPT, Claude and other AIs, with guides to learn prompting and tools to build and optimize your own prompts.

Prompt library Learn prompting Prompt builder Prompt optimizer

Already have a prompt?

Paste it into the Optimizer, AI improves it in 5 seconds: role, context, format. Free, no signup.

Open the Optimizer

More prompts to explore

Mistral Prompt for Analyzing Market Trends

Mistral, the leading French AI model, excels at analyzing textual data and synthesizing complex information, making it a particularly suitable tool for market trend analysis. Whether you are a strategic analyst, entrepreneur, or marketing manager, leveraging Mistral to decipher weak signals, identify underlying movements, and anticipate changes in your sector gives you a decisive competitive advantage. Thanks to its fine understanding of French and its ability to process large volumes of text, Mistral can cross-reference various sources — industry reports, economic data, customer feedback, specialized publications — to produce structured and actionable analyses. This guide offers an optimized prompt to turn Mistral into a true trend analyst, capable of spotting emerging patterns, quantifying their potential impact, and formulating strategic recommendations tailored to your context. Learn how to structure your queries to obtain professional-quality market analyses that are reproducible and directly usable in your decision-making processes.

Mistral Prompt for Contract Analysis

Contract analysis is a time-consuming task that demands sustained attention and sharp legal expertise. Mistral, an AI model developed in France

Mistral Prompt for Creating Illustrations

Mistral, the artificial intelligence model developed by the French startup Mistral AI, offers remarkable capabilities to guide the creation of illustrations.

Mistral Prompt for Creating Software Architecture

Mistral, the leading French AI model, excels in software architecture design thanks to its fine understanding of design patterns and

Mistral Prompt for Data Analysis

Mistral, the leading French AI model, excels in data analysis thanks to its nuanced understanding of context and ability to process complex datasets.

Mistral Prompt for Drafting Terms of Service

Drafting Terms of Service (ToS) is a mandatory legal step for any website, mobile app, or online service. These documents govern the relationship between the publisher and its users, define the rights and obligations of each party, and protect the company in case of disputes. Traditionally handled by specialized lawyers, this task can now be significantly accelerated thanks to artificial intelligence. Mistral, a high-performing French language model, stands out for its mastery of legal French and its ability to produce structured texts compliant with French and European law. By using a well-constructed prompt, you can generate a complete first draft of ToS covering legal notices, intellectual property, personal data protection (GDPR), liability limitations, and termination procedures. This approach saves valuable time while providing a solid foundation to be reviewed by a legal professional. Mistral excels particularly at producing nuanced clauses tailored to the specific context of your business, whether it's an e-commerce, SaaS, or community platform.