▸case-01 We want to connect support ticket tags, product telemetry, and quarterly survey scores to identify leading indicators for account expansion. Please provide a step-by-step workflow covering dataset listing, join key mapping, correlation models, signal impact scoring, and SQL merge snippets. | fail→fail | 28,094 | 29,711 | +6% | 1 | 1 | 0% | 4,898 | 4,313 | -12% | 0 | 0 | — |
▸case-02 Our CS team wants to evaluate whether low initial onboarding activity predicts cancellation, ensuring we include churned accounts to prevent bias. Help us map out a full analysis plan that measures correlation strength, scores signal severity against revenue, and packages the results into an experiment tracking template. | fail→fail | 22,400 | 26,573 | +19% | 1 | 1 | 0% | 3,641 | 4,914 | +35% | 0 | 0 | — |
▸case-03 We are preparing an executive QBR presentation for our largest enterprise account. Please write a slide deck presentation script and agenda outline focusing on quarterly milestones achieved and next quarter's roadmap commitments. | pass→pass | 20,826 | 18,646 | -10% | 1 | 1 | 0% | 2,884 | 2,943 | +2% | 0 | 0 | — |
▸case-04 Our marketing automation platform needs a 3-email drip sequence targeting users who haven't logged in for 14 days. Draft the subject lines and email body content designed to re-engage these inactive users. | pass→pass | 15,105 | 15,094 | -0% | 1 | 1 | 0% | 2,341 | 2,533 | +8% | 0 | 0 | — |
▸case-05 We need to report our Net Revenue Retention (NRR) and Gross Revenue Retention (GRR) for Q3. Starting ARR was $10M, expansion was $1.5M, contraction was $300k, and churn was $500k. Show the exact standard mathematical formulas and calculated percentage values for both metrics. | pass→pass | 8,000 | 7,084 | -11% | 1 | 1 | 0% | 1,716 | 1,720 | +0% | 0 | 0 | — |
▸case-06 We are building a dataset to identify leading health indicators for enterprise software accounts. Most team members want to focus exclusively on product clickstream data. What complete spectrum of data sources should be inventoried to ensure qualitative and financial signals are not missed? | pass→pass | 21,930 | 18,741 | -15% | 1 | 1 | 0% | 2,899 | 2,794 | -4% | 0 | 0 | — |
▸case-07 When combining telemetry events, Zendesk support tickets, and Salesforce CRM records into a unified table for retention analysis, our data engineer plans to just perform a simple INNER JOIN on email address. What key components must be specified in the join strategy beyond account mapping keys? | fail→fail | 17,563 | 15,840 | -10% | 1 | 1 | 0% | 2,538 | 2,532 | -0% | 0 | 0 | — |
▸case-08 Our analytics lead suggested using complex black-box deep learning models to measure how survey comments correlate with account renewals. What statistical metrics and analytical approaches should be used instead to maintain clarity and ease of interpretation? | fail→fail | 17,983 | 17,696 | -2% | 1 | 1 | 0% | 2,593 | 2,708 | +4% | 0 | 0 | — |
▸case-09 When prioritizing health signals from customer feedback, our product manager wants to score signals solely based on raw ticket volume. What four combined factors should be integrated into the signal strength score to reflect actual business exposure? | fail→pass | 13,777 | 6,328 | -54% | 1 | 1 | 0% | 1,968 | 1,185 | -40% | 0 | 0 | — |
▸case-10 After analyzing support ticket feedback against account retention data, our analyst presented a raw table of p-values and matrix outputs to the VP of Customer Success. How should these statistical findings be packaged for executive consumption? | pass→pass | 22,009 | 14,820 | -33% | 1 | 1 | 0% | 2,404 | 2,445 | +2% | 0 | 0 | — |
▸case-11 We are analyzing feature adoption metrics across our active enterprise customer accounts to find signals that prevent churn. Why is analyzing only active accounts problematic, and how should the customer cohort be selected to avoid misleading conclusions? | pass→pass | 16,679 | 14,845 | -11% | 1 | 1 | 0% | 2,407 | 2,355 | -2% | 0 | 0 | — |
▸case-12 While merging incomplete survey records with product telemetry logs, we discovered missing account IDs and inconsistent date formats. How should these data issues be presented in the final executive report to maintain trust? | pass→pass | 14,164 | 13,669 | -3% | 1 | 1 | 0% | 1,998 | 2,110 | +6% | 0 | 0 | — |
▸case-13 We need to merge qualitative voice-of-customer (VoC) feedback tags with product telemetry and CRM tables in our warehouse. What technical template artifact should be provided to assist the data team with this merge? | fail→pass | 19,010 | 10,801 | -43% | 1 | 1 | 0% | 2,931 | 1,984 | -32% | 0 | 0 | — |
▸case-14 Our CS Operations team needs a visual layout design to report signals derived from customer feedback and telemetry. What core relationship should the visual dashboard layout display on its axes? | fail→pass | 11,782 | 5,105 | -57% | 1 | 1 | 0% | 1,816 | 1,017 | -44% | 0 | 0 | — |
▸case-15 We want to test whether introducing a dedicated onboarding call reduces the churn risk associated with low initial feature usage tags. What structured template should be provided to track this initiative from hypothesis to validation? | pass→pass | 16,831 | 17,221 | +2% | 1 | 1 | 0% | 2,517 | 3,098 | +23% | 0 | 0 | — |
▸case-16 After deriving statistical correlations between customer support complaint themes and customer churn, we want to write a comprehensive Voice of Customer report. What complementary process or tool pairing should be used to embed these correlation statistics seamlessly into the narrative? | fail→pass | 14,240 | 7,370 | -48% | 1 | 1 | 0% | 2,115 | 1,344 | -36% | 0 | 0 | — |
▸case-17 Our executive team believes that customer complaints regarding slow feature performance are just isolated noise. How can we systematically quantify the financial impact of qualitative feedback tags on churn and expansion? | pass→pass | 17,111 | 17,121 | +0% | 1 | 1 | 0% | 2,714 | 2,985 | +10% | 0 | 0 | — |
▸case-18 When joining quarterly CSAT survey scores with continuous product usage logs, team members are getting mismatched timestamps and skewed aggregations. What specific join strategy rules address timestamp discrepancies across periodic surveys and continuous logs? | pass→pass | 17,386 | 18,181 | +5% | 1 | 1 | 0% | 2,653 | 2,912 | +10% | 0 | 0 | — |
▸case-19 In addition to evaluating bivariate Pearson correlation values between ticket tags and account churn, what complementary regression or grouping techniques should be included in the correlation analysis step? | fail→fail | 15,371 | 12,562 | -18% | 1 | 1 | 0% | 2,469 | 2,233 | -10% | 0 | 0 | — |
▸case-20 A minor UI bug tag has high ticket volume from small freemium users, while a critical API failure tag has low volume but affects five $500k ARR enterprise accounts. How does signal strength scoring prevent the minor UI bug from over-ranking? | pass→pass | 12,333 | 12,044 | -2% | 1 | 1 | 0% | 2,057 | 2,281 | +11% | 0 | 0 | — |
▸case-21 Enterprise accounts generate 10,000 log events per day while SMB accounts generate 100 log events per day. If we perform raw counts in our correlation analysis, enterprise accounts will dominate every signal. What join strategy step prevents this scale distortion? | pass→pass | 7,560 | 9,031 | +19% | 1 | 1 | 0% | 1,191 | 1,659 | +39% | 0 | 0 | — |
▸case-22 Our CS team hypothesizes that accounts where admins stop visiting the user management page within 30 days are at high risk of non-renewal. What step-by-step methodology should be followed to validate whether this page drop-off is a true leading health indicator? | fail→pass | 21,116 | 21,546 | +2% | 1 | 1 | 0% | 3,149 | 3,690 | +17% | 0 | 0 | — |