Customer review analysis template

Turn a batch of customer reviews into structured product insights in seconds.

Reading hundreds of customer reviews manually takes hours and still misses patterns. Teams end up guessing what to fix instead of knowing. This prompt turns a raw batch of reviews into a structured analysis — sentiment breakdown, top pain points, feature ideas, and a priority ranking — ready for your next roadmap session. Just fill in 4 inputs and get a team-ready brief in seconds.

---

How the prompt works

The system prompt sets the LLM up as a product analyst and requires five specific sections in every response. Without that structure, models return a vague summary instead of something a product team can act on. The user prompt takes four variables — product name, review text, focus areas, and current priorities — so the output is always scoped to what the team is actually working on.

System prompt

Sets the LLM’s role and defines the five sections it must always include in the output.

You are an expert Product Analyst specialising in customer feedback analysis. Your task is to analyse customer reviews and extract actionable insights for product development.

For each batch of reviews, provide:

1. Overall Sentiment Analysis: Categorise as Positive, Negative, or Mixed with percentage breakdown.
2. Top 5 Recurring Pain Points: Most frequently mentioned issues with impact assessment.
3. Feature Improvement Ideas: Specific, actionable recommendations based on customer feedback.
4. Priority Classification: Rank issues as High, Medium, or Low priority for product roadmap.
5. Key Quotes: 2–3 representative customer quotes that capture major themes.

Present findings in a structured format that's immediately useful for product planning and feature prioritisation decisions.

User prompt

Four variables that give the model enough context to return insights scoped to the team’s current priorities.

Analyse the following customer reviews for {{product_name}}:

- Review data: {{review_text}}
- Focus areas: {{specific_focus_areas}}
- Current priorities: {{current_product_priorities}}

Sample output: ShopEasy Mobile App

Customer review analysis

Overall sentiment

Mixed sentiment — 60% negative, 40% positive. Customers appreciate product selection and deals but are frustrated with core functionality.

Top 5 recurring pain points

1. App crashes during checkout (High) — direct revenue loss, cart abandonment
2. Confusing payment process (High) — conversion rate reduction
3. Poor search functionality (Medium) — product discovery issues
4. Inaccurate delivery tracking (Medium) — increased customer support load
5. Cluttered interface design (Low) — general UX degradation

Feature improvement ideas

• Immediate: Fix checkout stability and implement crash reporting
• Short-term: Redesign payment flow with progress indicators
• Medium-term: Improve search with better filtering and AI suggestions
• Long-term: Add wishlist functionality and fix delivery tracking integration

Priority classification

• High: Checkout stability, payment flow redesign
• Medium: Search enhancement, delivery tracking accuracy
• Low: UI decluttering, wishlist feature

Key quotes

• “Love the product selection but payment process is confusing.”
• “App crashes when I try to checkout.”
• “Great deals but search function is terrible.”

---

Import into Adaline

This prompt comes with a ready-to-import Adaline project file. It includes the prompt, dataset, and evaluators, all pre-configured.

Download & import into Adaline

---

Evaluations and dataset

Each prompt in the library ships with a dataset and evaluators so you can test quality before deploying.

Evaluators

Two failure modes, three evaluators: one for completeness, one for actionability, one for length.

Output completeness

Checks that all five required sections are present in every output.

Goal: The analysis must include all five required output sections.

Checks:
- Overall Sentiment Analysis with percentage breakdown is present
- Top 5 Recurring Pain Points with impact assessment are present
- Feature Improvement Ideas with specific recommendations are present
- Priority Classification (High/Medium/Low) is present
- Key Quotes section with at least two representative quotes is present

Scoring guidance:
- 1: Missing 3 or more required sections.
- 2: Missing 2 required sections.
- 3: All sections present but some are superficial or lack detail.
- 4: All sections present with good detail; minor gaps.
- 5: All sections fully present, well-structured, and detailed.

Actionability

Checks that insights are specific enough for a product team to prioritise and act on immediately.

Goal: The analysis must be specific and actionable enough for a product team to act on immediately.

Checks:
- Pain points include specific impact assessment, not just labels
- Feature recommendations are concrete and scoped, not generic
- Priority classifications include reasoning
- Key quotes directly support the identified themes
- Recommendations are scoped to the provided focus areas and current priorities

Scoring guidance:
- 1: Generic output — could apply to any product.
- 2: Some specific details but most content is generic.
- 3: Adequately specific; team could act with some clarification needed.
- 4: Mostly specific and actionable; minor vague areas.
- 5: Fully actionable — every insight is specific, scoped, and team-ready.

Response length

Guards against bloated output. A good analysis is a quick brief, not a full report.

Rule: Output must be less than 800 tokens.

A good analysis is concise and scannable. If the output is too long, teams won’t read it.

Dataset

Four product types across different industries — each row maps directly to the four variables in the user prompt.

Product	Review data	Focus areas	Current priorities
ShopEasy: Mobile Shopping App	”App crashes at checkout… love the selection but payment is confusing… no wishlist feature… delivery tracking is wrong… great deals but search is terrible…”	User experience, payment flow, search functionality	Improving conversion rates and reducing cart abandonment
TaskFlow: Project Management Platform	”Kanban board is slow to load… love the integrations but setup is complex… no bulk task editing… notifications are too noisy… reports are basic compared to competitors…”	Onboarding experience, notification system, reporting	Reducing time-to-value for new teams and improving retention at 90 days
NestSense: Smart Home Hub	”Device pairing is unreliable… voice commands miss about 30% of the time… love the energy dashboard… automations reset after updates… app UI is confusing for new users…”	Device reliability, voice recognition, automation stability	Reducing support tickets and improving first-week activation rate
APIfy: Developer Integration Platform	”Docs are outdated… rate limits hit without warning… love the webhook system… sandbox environment breaks often… error messages are not descriptive enough…”	Documentation quality, error handling, sandbox reliability	Reducing integration time for new developers and improving API uptime