Skip to main content
Sprig MCP works in both directions: build and launch Studies from your AI client, and pull results back out to analyze and act on. Try these prompts in any connected AI client once Sprig MCP is set up.

​
Build and launch Studies

Create a Study, refine it, and take it live, all from the conversation.
  1. Create a study Create a 5-question In-Product Survey to learn why users abandon checkout. Use an NPS, an open text asking the reason for the score, and a Rating Scale on checkout ease. Route anyone who scores 6 or below to the reason question.
  2. Create from a research goal Create a Sprig study to understand why users are dropping off during onboarding. Keep it to five questions or fewer.
  3. Edit a specific question Change Question 2 to a 5-point rating scale with labels from Very difficult to Very easy.
  4. Add skip logic Add skip logic so anyone who picks Less than 15 minutes goes to the end of the survey.
  5. Add display logic Show the improvement question only to respondents who picked Payment details in the previous question.
  6. Randomize answer options Randomize the answer options on Question 3, and make Questions 1 and 2 required.
  7. Remove a question Delete the last question. (If other questions route to it, Sprig refuses the delete until the logic is resolved, so your branching never silently breaks.)
  8. Translate Translate this study into Spanish and Japanese. Fill in only the missing text, do not replace existing translations.
  9. Create invitation links Create 2,000 invitation codes for the beta cohort so I can distribute this survey by link.
  10. Set In-Product Survey targeting List the events I can target, then show this survey to users who trigger checkout_abandoned, on the enterprise plan, with a 10 second delay.
  11. Run a bias check Review this study for leading questions, double-barreled questions, and missing answer options.
  12. Validate before launch Validate this study and list anything blocking launch. Keep it in draft for my review.
  13. Launch, pause, and resume Launch the study. Then later: Pause the study, translate it into French, and resume it.

​
Analyze results

  1. Summarize a study Summarize the key themes from my most recent Sprig study and highlight the top 3 issues users mentioned.
  2. Extract NPS insights Pull all NPS studies from Sprig in the last 30 days. What are the most common reasons users gave for low scores?
  3. Compare studies over time Compare the results from my Q1 and Q2 onboarding surveys in Sprig. What changed?
  4. Segment analysis From my latest Sprig study, show me how responses differ between power users and new users.
  5. Feature feedback digest Pull all Sprig responses that mention [feature name] and summarize what users are asking for.
  6. Draft a research summary doc Using my latest Sprig study results, write a one-page research summary I can share with my team.
  7. Turn feedback into hypotheses Based on the open-text responses in my latest Sprig study, generate 5 product hypotheses I could test next.
  8. Prioritize from feedback From my Sprig study on checkout experience, rank the top pain points by frequency and suggest which to fix first.
  9. Prep for a research readout Using my Sprig study results, create a bullet-point readout I can present in a 10-minute team meeting.
  10. Look up a specific study Find the Sprig study titled [study title] and show me its questions and response count.

​
Close the loop

Combine both directions in one conversation: analyze what came back, then field the follow-up.
  1. From findings to follow-up study Based on the top pain point in my checkout study results, create a follow-up study that digs into that specific issue.
  2. From launch to monitoring Validate and launch the study we just built, then tell me when I should check back based on the response target.

​
MCP to MCP: connecting Sprig with other tools

When both Sprig and another tool are connected to the same AI client, you can run workflows that span both, pulling data from Sprig and acting on it in another system automatically.
Note: MCP to MCP workflows require both Sprig and the destination tool to be connected in the same AI client. Check that both connections are active before running these prompts.
  1. Sprig + Linear Summarize the top 5 pain points from my latest Sprig study and create a Linear issue for each one, assigned to the product team.
  2. Linear + Sprig Take the open questions in this Linear project description and create a Sprig study that answers them.
  3. Sprig + Jira Pull negative responses from my Sprig checkout study and create Jira tickets with the user quotes as description text.
  4. Sprig + Notion Fetch my latest Sprig study results and write a research summary into my Notion research repository page.
  5. Notion + Sprig Turn the research questions in my Notion research plan into a draft Sprig study, one question per research goal.
  6. Sprig + Figma Pull the top usability issues from my Sprig study on the onboarding flow and add them as comments on the relevant Figma frames.
  7. Sprig + Slack Every time a Sprig study gets more than 50 responses, post a summary of the top themes to the #product-research Slack channel.
  8. Sprig + HubSpot Find all Sprig respondents who gave an NPS score below 6 and update their HubSpot contact record with a ‘detractor’ tag.
  9. Sprig + Salesforce Pull Sprig survey responses from enterprise-tier users and log the key feedback as activity notes on their Salesforce account records.
  10. Sprig + Google Sheets Export all responses from my latest Sprig study into a new Google Sheet, with one row per response and columns for question, answer, and segment.
  11. Sprig + Confluence Pull my last 3 Sprig studies and write a quarterly research digest page in Confluence summarizing key findings across all three.
  12. Sprig + GitHub From my Sprig developer experience study, extract bug reports and usability issues and create GitHub issues with appropriate labels.