Mine G2 reviews of a prospect's product to learn their pains
Mines public reviews of your prospect's own product to reveal what their internal teams get beaten up about: complaint clusters with frequency and severity, who inside the company owns each pain, whether it's growing, and which pains your product genuinely addresses. It's discovery intel gathered before anyone takes your call.
You are a voice-of-customer analyst with a twist: you're not mining reviews of my product — you're mining reviews of my PROSPECT's product, because what their customers complain about is what their product and CS teams get beaten up about internally every week. I'll paste G2 (or Capterra/TrustRadius) reviews of the prospect's product. You produce: 1. COMPLAINT CLUSTERS — group the negative and lukewarm feedback into 3 to 5 themes, each with: a name, rough frequency, 1 to 2 near-verbatim snippets, and severity (deal-breaker vs annoyance) as reviewers frame it. 2. PRAISE BASELINE — 2 lines on what customers love, because pain lands differently when I know what they're protecting. 3. TREND READ — if the reviews span time, whether each complaint cluster is growing, stable, or fading. Mark as unknown if dates are thin. 4. INTERNAL WEATHER — for each major cluster, who inside the prospect's company owns that pain (product, CS, engineering, sales taking the hit in deals) and how it probably shows up in their quarter. 5. RELEVANCE MAP — which clusters my product can actually help with, honestly graded, and which are simply useful context for empathy. 6. THE OPENER — one email-ready observation for my best-fit cluster that demonstrates insight without quoting their bad reviews at them like a threat. Rules: never fabricate review content — work only from what I pasted. Distinguish reviewer segments if visible (SMB vs enterprise reviewers often complain about different things). No gloating tone anywhere; their bad reviews are my empathy material, not ammunition. Before you analyze, interview me. Ask me these questions ONE AT A TIME, waiting for my answer each time: 1. Whose product are we analyzing, and what does it do? 2. Paste the reviews — prioritize 3-and-4-star ones; they're the most specific. Include dates if shown. 3. What do you sell, and which of their internal teams would buy it? 4. What's your goal — cold outreach angle, discovery prep, or account strategy? Once you have my answers, run the analysis.
How to use it
- 1
Copy the prompt into Claude, ChatGPT, or any LLM.
- 2
Collect 15-30 reviews of the prospect's product from G2 or Capterra — 3-and-4-star reviews are the goldmine; pure 1-stars are often rage, pure 5-stars are often fluff.
- 3
Paste review text with dates, and answer the interview with which internal team you sell to.
- 4
Use INTERNAL WEATHER to sharpen your targeting — the team absorbing the complaints is often a better entry point than the org chart suggests.
- 5
Deploy the opener with empathy framing; never let outreach read like you're waving their bad reviews at them.
Best practices
Copy reviews manually rather than asking the model to browse review sites — G2 and Capterra block most scraping, and pasted text is verifiable anyway.
The 3-star review is the analyst's favorite: balanced enough to be credible, annoyed enough to be specific.
Check the RELEVANCE MAP grades honestly — using a complaint cluster you can't actually help with sets up a discovery call you'll lose.
This works double-duty for competitive deals: run it on the incumbent you're displacing and you have the dissatisfaction map for the whole account.
Example: what this looks like in practice
An AE sells API-monitoring tooling and targets a mid-market SaaS company. She pastes 24 G2 reviews of the prospect's product; the model clusters complaints into 'integration breakage' (9 mentions, growing, severity high), 'slow support response,' and 'reporting gaps.' INTERNAL WEATHER maps integration breakage to their platform engineering team — her exact buyer. RELEVANCE MAP grades it a strong fit and the other two as context only. Her opener: 'Teams running as many integrations as you do usually feel breakage before their customers report it — is that visibility something your platform team has today?' The engineering director takes the meeting and opens with 'funny timing.'
Best fit
This prompt is one gear in a bigger machine. We orchestrate 20+ tools into outbound systems our clients own — and guarantee the results.
Apply for a Pilot Spot → →Frequently asked questions
Two ways. Reviews of a prospect's own product reveal what their product, CS, and engineering teams are being hammered about internally — pain intel no cold call surfaces that fast. And reviews of an incumbent you're displacing map the dissatisfaction inside your deal. Either way, customers have already done your discovery; this prompt structures it.
More account & prospect research prompts
Build a 10-minute company deep-dive brief before you touch an account
Produces a one-page, source-backed account brief with a fixed six-section structure: snapshot, revenue logic, recent momentum, evidence-based pressures, two outreach angles, and landmines to avoid. It compresses the hour of tab-hopping most reps do before a tier-one account into ten minutes, and forces every claim to carry a source.
Scan an account for trigger events: news, funding, leadership moves, layoffs
Runs a structured six-month trigger-event sweep on one account — funding, leadership changes, layoffs, launches, expansion, legal news — and returns a dated, sourced signal log, the top three events ranked by outreach value, a ready-to-adapt angle for the best one, and an honest timing call including 'no trigger exists.' It turns 'why now' from a guess into evidence.
Audit a prospect list for quality before a single email goes out
Audits a prospect list before launch: completeness and duplicates, out-of-ICP rows, stale-data risks, deliverability hazards like role-based emails and sequence collisions, and an honest A-F grade with a prioritized fix list. It catches the problems that get misdiagnosed as 'copy issues' three weeks and one burned domain later.