Customer Review Mining: Personas, Jobs-to-Be-Done, Objections and Verbatim Copy Phrases

Turns pasted customer reviews into evidence-based personas, jobs-to-be-done, objections and a bank of exact customer phrases ready to reuse in copy.

You get: Data snapshot, persona table and objections table

More like this

Ready to use: no blanks to fill in.

The prompt

customer-review-mining-personas-jobs-to-be-done-objections-and-verbatim-copy-phrases.md
You are a senior customer insights analyst working with a marketing team. Your job is to turn raw customer reviews into personas, jobs-to-be-done, objections and reusable customer language, so I can decide which audience and message to lead with in copy.

Start by asking me, in one short message, what the product is and who sells it, and to paste the reviews (ideally 30 or more, with ratings or dates if available). Do not continue until I answer.

Rules:
- Use only what the reviews say. Label any inference as an Assumption and keep it separate from evidence.
- Quote customers verbatim in quotation marks. Never polish or paraphrase a quote.
- Write each job-to-be-done as: When [situation], I want to [motivation], so I can [outcome].
- Mark any persona backed by fewer than 3 reviews as low confidence.

Output format:
1. Data snapshot: review count, rating mix, obvious gaps or bias.
2. Persona table: name, who they are, job-to-be-done, trigger, desired outcome, review count, confidence.
3. Objections table: objection, exact quote, personas affected, suggested copy response.
4. Copy bank: 10 verbatim phrases grouped as hooks, proof and objection handlers.
5. Risks and missing information, then 3 next actions, including which persona to test first.

Example output

AI-written example

1. Data snapshot

  • 42 reviews, Jan to Jun, average 4.4★ (5★: 27, 4★: 8, 3★: 3, 2★: 2, 1★: 2)
  • Bias: 9 reviews mention a first-order discount code, so some may be incentivized. Only 4 reviewers mention cancelling or pausing.

2. Personas

PersonaWhoJob-to-be-doneTriggerOutcomeReviewsConfidence
Café-QuitterRemote workers cutting daily coffee spendWhen I'm tempted by the morning café run, I want a quality coffee at home, so I can save money without feeling deprivedRising café billsCafé taste for less17High
Time-Starved ParentParents with early morningsWhen mornings are chaotic, I want coffee ready in seconds, so I can get the kids out the doorNewborn or school runZero-prep caffeine9High
Gift BuyerGifting to coffee loversWhen I need a gift fast, I want something that looks premium, so I can look thoughtfulBirthday or holidayGift that impresses2Low

3. Objections

ObjectionExact quotePersonasCopy response
Price per bottle"Not cheap, but cheaper than my $6 oat latte habit"Café-QuitterShow cost per cup beside café price
Too strong or bitter"Way too strong until I figured out the 1:3 ratio"AllPut the dilution guide on the product page
Subscription lock-in"Skipping a delivery took me three clicks, which I did not expect"Parent, Café-QuitterPromote easy skip and pause

4. Copy bank

Hooks

  1. "Fired my barista, kept the taste"
  2. "Mornings finally feel manageable"
  3. "Better than the café down the street"

Proof

  1. "I haven't bought a coffee out in five weeks"
  2. "Tastes smooth, zero bitterness over ice"
  3. "My husband thought I'd been to a café"

Objection handlers

  1. "Cheaper than my $6 oat latte habit"
  2. "Skipping a delivery took me three clicks"
  3. "Once I got the ratio right, it was perfect"
  4. "Arrived cold and sealed, no leaks"

5. Risks and next actions

Risks and missing information

  • Assumption: Café-Quitters are mainly remote workers. Only 6 of the 17 mention working from home.
  • No data on age, income or repeat purchase rate.
  • Discount-code reviews may overstate satisfaction.

Next actions

  1. Test the Café-Quitter persona first, using the cost-per-cup hook against the "fired my barista" hook.
  2. Add the dilution ratio and the easy-skip message to the product page.
  3. Collect 20 or more reviews from non-discount and churned customers to validate the Parent and
Generated from this prompt by AI. Your results will vary.

Tips and common edits

Use when you are writing landing page, ad or email copy and want it grounded in real customer language. Paste 30 or more reviews from one product, removing names or other personal details first.

Questions about this prompt

More in AI Marketing

90-Day Lifecycle Marketing Diagnostic and Experiment Roadmap for Onboarding and Retention

Diagnoses drop-off across the customer lifecycle from your funnel data and produces a prioritized 90-day plan of messages, triggers, and experiments with metrics so teams can decide where to invest first.

Five-Angle Meta and Google Ad Copy Generator with Character Counts and A/B Test Plan

Produces Meta and Google ad copy across five distinct angles within platform character limits, plus a simple test plan with decision rules.

One-Page Brand Voice Brief Builder from Copy Samples for ChatGPT, Claude and Gemini

Analyzes your brand copy samples and builds a reusable one-page voice brief with tone rules, banned words, example rewrites and a paste-ready instruction block.

Positioning and Messaging Hierarchy Builder from Competitor and Customer Evidence

Turns your product facts, customer evidence, and competitor notes into a tested positioning statement, messaging hierarchy, and proof-gap list so a marketing team can decide what to say and what to validate first.

Audience Research Source Discovery and Evidence Synthesis for Segment Prioritization

Guides you to plan source discovery, review the evidence you collect, build a citation table, and synthesize findings into a segment prioritization decision, without pretending the model browsed the web.

Above-the-Fold Landing Page Critique with 3 Headline, Subhead, and CTA Variants

Critiques landing page copy for clarity and conversion, then rewrites the headline, subhead, and CTA in three distinct variants.

Competitor and Audience Evidence Review with Citation Table and Go/No-Go Brief

A research workflow that plans online source discovery, scores evidence, builds a citation table, and ends with a decision brief, without pretending live browsing happened.

Customer Voice Synthesis from Reviews and Forum Threads

Turns pasted reviews, support threads, and forum posts into coded themes, representative evidence, and a ranked list of product or messaging decisions.

Eight-Objection Handling Playbook: Acknowledge, Ask, Reframe, Evidence

Builds a playbook that answers the eight most likely objections for your product and buyer, each in four steps with honest evidence.

LinkedIn Post from a Work Lesson, No Engagement Bait

Turns a work story or lesson into a LinkedIn post with a strong first line, short paragraphs, and one clear takeaway.

Meta Title and Description Variants: 5 Click-Angle Pairs Within Limits

Writes 5 meta title and description pairs within character limits, each using a different angle to earn the click.

Pricing Pushback Response Playbook with Value Reframe and Concession Rules

Diagnoses what a price objection really means and builds response scripts, trade-based concession rules, and escalation criteria. It helps a rep decide whether to hold price, trade scope, or walk away.