# Mine review videos for user pain

> Reviewers narrate friction in real time; harvest the "why is this so hard" moments across your category.

- For: PM
- Category: Product & UX Research
- MCP tools: deep_search, library_import_youtube_video, get_youtube_transcript
- HTML version: https://veridive.com/mcp/use-cases/user-pain-mining

## The problem

The most honest user research in your category runs continuously, unpaid, on camera: reviewers using products — yours and your rivals' — while narrating exactly what they think. "Why is this setting buried here." "This took me three tries." "Nobody will find this feature." It's think-aloud protocol, the gold standard of usability research, performed publicly at scale — and PM teams pay agencies for lab versions of it while the free corpus grows unread.

The pain points in those narrations are roadmap input of the best kind: unprompted, specific, and demonstrated rather than recalled. A user *saying* they struggled in a survey is data; a reviewer *struggling on camera* while explaining why is evidence.

## How veridive MCP helps

**deep_search** finds the friction moments across your category: transcript-level search means "videos where reviewers struggle with <workflow>" returns those exact narrations, evidence-timestamped — across your product, your rivals', and the category's generic tooling.

**library_import_youtube_video** and **get_youtube_transcript** turn the richest sessions into analyzable text: import, pull the verbatim narration, and harvest the pain inventory — what they struggled with, what they said while struggling, what they tried first (your users' mental model, documented). The output reads like a usability-lab report, sourced from sessions nobody had to schedule, recruit or pay for.

## How to run it

1. **Connect veridive MCP** — One-time setup: add the veridive MCP server to Claude, ChatGPT, Cursor or any MCP client and generate your API key. Takes about two minutes.
2. **Sweep for friction narrations** — The category's review and hands-on content, searched for struggle moments — not marketing summaries.

   ```
   Find review and hands-on videos where people struggle with or complain about <workflow/product area> — the moments of friction, not the overviews — use veridive's deep_search.
   ```
3. **Harvest the pain inventory** — Import the richest sessions, pull the narrations verbatim — the think-aloud data, in text.

   ```
   Import these and pull the transcript passages where the reviewer hits friction — what they struggled with, what they said, what they tried first: <video URLs>
   ```
4. **Structure it for the roadmap** — Pain points grouped, counted across reviewers, and quoted — evidence the prioritization meeting can't wave away.

   ```
   Group these friction moments by theme, note which recur across multiple reviewers, and keep the strongest verbatim quote per theme.
   ```

## Problems it solves

- Think-aloud usability data exists at scale, free, and PM teams only see the lab version they paid for.
- Surveys collect recalled pain; reviewers demonstrate it live, with the failed attempts included.
- Rival products' friction — your opportunity list — is narrated publicly and mined by nobody.
- Prioritization debates run on internal anecdotes when cross-reviewer counts were available.

## Why it's valuable

- Usability-lab-grade evidence from sessions nobody scheduled or paid for.
- The failed-first-attempt layer reveals users' actual mental models — the hardest data to collect.
- Recurrence counts across reviewers turn anecdotes into prioritizable signal.
- Rival friction mining doubles as your differentiation backlog.

## Example prompts

```
Videos where reviewers struggle with <workflow> — friction moments — use veridive's deep_search.
```

```
Import these; pull verbatim friction narrations with what they tried first: <URLs>
```

```
Group by theme, count recurrence, keep the strongest quote each.
```

## FAQ

**How does this compare to session-replay tools?**

Replay shows what users did; reviewers narrate why — the layer replay can't capture. And it covers your competitors' products, which your instrumentation never will.

**Which tools does the mining chain?**

deep_search locates the friction moments (evidence timestamps), then library_import_youtube_video + get_youtube_transcript for verbatim narration — free to pull once imported.

**Is reviewer pain representative of real users?**

Reviewers are power users, so weight accordingly — friction that stops a reviewer will wall out a normal user. Recurrence across several reviewers is the strongest signal in the file.

## Related use cases

- [Treat tutorials as free usability tests](https://veridive.com/mcp/use-cases/tutorials-as-usability-tests.md) — Every workaround a tutorial teaches is a usability bug report; collect and query them across your product's ecosystem.
- [Find the niche creators reviewing your competitors](https://veridive.com/mcp/use-cases/niche-reviewers-of-competitors.md) — Skip the sponsored mega-channels: surface small, credible reviewers whose honest takes reveal what users really trip over.
- [Steal your customer's exact words](https://veridive.com/mcp/use-cases/voice-of-customer-phrasing.md) — Mine how real users describe the problem in reviews and vlogs — copy that converts is usually a transcript quote.

---

Part of the veridive MCP use-case library: https://veridive.com/mcp/use-cases.md
Server docs for agents: https://veridive.com/mcp.md