# Treat tutorials as free usability tests

> Every workaround a tutorial teaches is a usability bug report; collect and query them across your product's ecosystem.

- For: UX researcher
- Category: Product & UX Research
- MCP tools: deep_search, library_import_youtube_video, deep_context
- HTML version: https://veridive.com/mcp/use-cases/tutorials-as-usability-tests

## The problem

Third-party tutorials about your product are a document your team never reads correctly. You see them as flattering ecosystem content; they're actually usability bug reports with production values. Every step a tutorial slows down to explain is a step your interface failed to explain. Every "make sure you click X first, or it won't work" is a sequence error your design permits. Every workaround taught to thousands of viewers is a missing feature with measured demand.

The tutorial ecosystem is your product's shadow documentation — written by outsiders, shaped entirely by where real users need rescuing. Read as UX research, it's a continuously updated map of exactly where your product fights its users.

## How veridive MCP helps

**deep_search** collects the shadow documentation: tutorials and how-to content about your product (and your rivals'), transcript-searched so "tutorials that explain how to work around <limitation>" finds the confession directly.

**library_import_youtube_video** pins the corpus; **deep_context** interrogates it like a research repository: *"which steps do tutorials consistently slow down on? what warnings do they repeat? which workarounds get taught?"* — answers **cited to the tutorials**. The findings read as a usability audit conducted by your ecosystem: friction ranked by how many independent tutorials address it, each item with the exact clip for the design review.

## 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. **Collect the shadow docs** — Third-party tutorials about your product — the rescue content, not your official videos.

   ```
   Find third-party tutorials and how-to videos about <your product> — especially setup guides and 'how to actually do X' content — use veridive's deep_search.
   ```
3. **Import and interrogate** — The corpus becomes a queryable research repository — asked like a UX researcher would.

   ```
   Import these, then: which steps do the tutorials slow down to explain, what warnings do they repeat, and what workarounds do they teach? Cite the videos and moments: <video URLs>
   ```
4. **Rank by independent confirmation** — Friction addressed by many independent tutorials is friction with measured reach.

   ```
   Rank the friction points by how many independent tutorials address them — that's the usability priority list, with the clips.
   ```

## Problems it solves

- Third-party tutorials get read as flattery when they're bug reports with reach numbers.
- Usability studies sample a dozen users; the tutorial ecosystem documents thousands' worth of rescue demand.
- Workarounds taught at scale are feature requests nobody filed.
- Design reviews debate friction that tutorials have already mapped, with clips.

## Why it's valuable

- A continuously updated usability audit, authored by your ecosystem for free.
- Independent-confirmation counts rank friction by real-world reach.
- Every finding carries its clip — design reviews watch the confession, not a summary.
- The rival pass works identically: their shadow docs are your competitive gap list.

## Example prompts

```
Third-party tutorials about <product>, especially rescue content — use veridive's deep_search.
```

```
Import these; what do tutorials slow down on, warn about, work around? Cited: <URLs>
```

```
Rank friction by independent-tutorial count — the priority list with clips.
```

## FAQ

**Our official tutorials cover these steps — doesn't that solve it?**

Official tutorials are part of the same signal: needing a video to complete a flow is the finding. The third-party layer adds the unfiltered version — what outsiders think needs explaining, in the order users actually get stuck.

**How does this relate to the onboarding-benchmark use case?**

Same insight, different scope: the benchmark compares first-run friction across competitors for strategy; this audits your product's full surface for UX priorities. The benchmark is a comparison; this is a repository.

**How often should the corpus refresh?**

Per release cycle — new versions spawn new rescue content fast, and a tutorial teaching an outdated workaround tells you your fix shipped but its discoverability didn't.

## Related use cases

- [Benchmark your onboarding against rivals' tutorials](https://veridive.com/mcp/use-cases/onboarding-benchmark.md) — Collect competitors' getting-started videos and query them side by side: where do users need hand-holding your flow avoids — or shares?
- [Mine review videos for user pain](https://veridive.com/mcp/use-cases/user-pain-mining.md) — Reviewers narrate friction in real time; harvest the "why is this so hard" moments across your category.
- [Build support FAQs from how-to videos](https://veridive.com/mcp/use-cases/faq-from-howto-videos.md) — The questions tutorials answer are the tickets you'll receive; draft deflection docs from them before launch.

---

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