> For the complete documentation index, see [llms.txt](https://help.dscout.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.dscout.com/dscout-ai/dscout-mcp/dscout-mcp-prompt-library.md).
# Dscout MCP prompt library
To spark inspiration when using the Dscout MCP, we've compiled a prompt library to kickstart your conversations.
Below, you'll find starter prompts for simpler tasks the MCP can take off your plate and prompts to help you build multi-step workflows directly in your AI tool of choice.
{% hint style="success" %}
**Tip:** Copy a prompt and paste it into your chosen AI tool's chat window, customizing the text in brackets to fit your specific research.
{% endhint %}
### Starter prompts
These prompts focus on smaller tasks the MCP can quickly streamline for you, helping you complete quick tasks from your to-do list.
#### Drafting
{% prompt description="Draft a new usability test" defaultExpanded="full" %}
```markdown
Draft a usability test to learn how [audience] reacts to [feature/prototype], including 3 screener questions to qualify them.
```
{% endprompt %}
{% prompt description="Modify a usability test" defaultExpanded="full" %}
```markdown
Add a task to my study where participants complete [flow], asking them to rate how easy or difficult they found the task.
```
{% endprompt %}
#### Recruitment and launch readiness
{% prompt description="Set incentive and check launch readiness" defaultExpanded="full" %}
```markdown
Set the incentive for [study] to [incentive] and tell me if anything is blocking launch.
```
{% endprompt %}
{% prompt description="Flag bad-fit applicants" defaultExpanded="full" %}
```markdown
Show me the applicants for [screener] ranked by fit, flagging any who don't match my target criteria.
```
{% endprompt %}
#### Analysis
{% prompt description="Pull quotes with sources" defaultExpanded="full" %}
```markdown
Pull direct quotes from [study] where participants struggled with [flow], providing sources for each quote.
```
{% endprompt %}
{% prompt description="Compute completion metrics" defaultExpanded="full" %}
```markdown
Compute the completion rate and average time-on-task for [flow/task].
```
{% endprompt %}
{% prompt description="Filter responses by topic" defaultExpanded="full" %}
```markdown
Filter entries in [study] where participants mentioned [topic], and show me who those participants are.
```
{% endprompt %}
{% prompt description="Summarize response themes" defaultExpanded="full" %}
```markdown
Summarize the top 3 themes from [study], with supporting quotes and sources.
```
{% endprompt %}
{% prompt description="Compare responses from multiple studies" defaultExpanded="full" %}
```markdown
Compare [metric] between [studyA] and [studyB].
```
{% endprompt %}
{% prompt description="List clips from responses" defaultExpanded="full" %}
```markdown
Grab clips from [study] showing the moments participants got confused.
```
{% endprompt %}
#### Working with prototypes
{% prompt description="Address pain points directly in Figma Make" defaultExpanded="full" %}
```markdown
Assess the top pain points from [study] and suggest changes to my prototype to address them.
```
{% endprompt %}
{% prompt description="Build a study based on a Figma Make prototype" defaultExpanded="full" %}
```markdown
Take the most recent version of my [prototype] and draft a Dscout usability test focusing on my latest design.
```
{% endprompt %}
####
#### Study reuse
{% prompt description="Duplicate a study" defaultExpanded="full" %}
```markdown
Clone [study] for next quarter's follow-up round.
```
{% endprompt %}
### Multi-step workflow prompts
These prompts combine several tasks in one request rather than separating them out like the prompts above. Use these when you've acclimated to using the Dscout MCP and are ready to use it for more complex workflows.
{% prompt description="Clone and launch a study with new recruitment criteria" defaultExpanded="full" %}
```markdown
Find a study related to [topic], clone it, update the incentive to [incentive] and swap in [criteria]. Then, launch it as a new usability study, keeping everything else the same.
```
{% endprompt %}
{% prompt description="Create new study from previous findings" defaultExpanded="full" %}
```markdown
Look at [study]'s results, pull out the top pain points, and draft a new usability study that specifically tests fixes for those.
```
{% endprompt %}
{% prompt description="Compare studies and create a follow-up" defaultExpanded="full" %}
```markdown
Compare [studyA] and [studyB] on [metric]. If [studyB] performs worse, clone [studyA]'s setup for a follow-up round targeting the same audience.
```
{% endprompt %}
{% prompt description="Clone and launch a study with new tasks" defaultExpanded="full" %}
```markdown
Take [study], create a new version that removes [task] and adds [task]. Then, launch this new version as a separate study without touching the original.
```
{% endprompt %}
{% prompt description="Summarize cross-mission findings" defaultExpanded="full" %}
```markdown
Across the studies in [project], find every place participants ran into [problem]. Then, summarize what they said, with sources.
```
{% endprompt %}
{% prompt description="Identify outliers in a specific timeframe" defaultExpanded="full" %}
```markdown
Compare [metric] across all my usability tests in [timeframe], and tell me which ones are outliers.
```
{% endprompt %}
### Learn more
Learn more about the Dscout MCP in these articles:
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.
Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:
```
GET https://help.dscout.com/dscout-ai/dscout-mcp/dscout-mcp-prompt-library.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.