Design and Analyze NPS Survey Frameworks

NPS Survey Framework Expert enables Claude to design, implement, and analyze comprehensive Net Promoter Score survey systems with advanced segmentation and actionable insights, covering survey methodology, customer segmentation, statistical analysis, and translating NPS data into business insight. It documents the standard NPS question, "How likely is it that you would recommend [company/product/service] to a friend or colleague?" on a 0-10 scale, score categories, Promoters 9-10, Passives 7-8, Detractors 0-6, and the NPS formula, percent Promoters minus percent Detractors, ranging from -100 to +100, plus three timing strategies: relationship NPS measured quarterly or bi-annually, transactional NPS after purchase, support, or onboarding, and touchpoint NPS at specific interaction points.

Use it to design an NPS program end to end: question structure covering the core NPS question, an open-ended "why" follow-up, an optional categorical driver question, and 2-3 segmentation questions; B2B, feature-specific, and competitive question variations; segment-triggered distribution logic; response-rate optimization covering send timing, subject lines, mobile optimization, and a capped reminder sequence; statistical sample-size calculation; SQL for NPS-by-segment analysis; a qualitative-analysis process covering theme clustering, sentiment scoring, impact/effort prioritization, and 5-why root cause; a detractor and promoter response playbook; industry benchmarks by vertical; executive and operational dashboard KPIs; and trend analysis with statistical significance testing. Its common-pitfalls guidance flags what to avoid: surveying the same customer within 90 days, missing bot or duplicate-response controls, reporting NPS with under 30 responses, and treating NPS correlation with business outcomes as causation.

Input is an NPS program requirement - target segment, survey timing type, and what level of analysis is needed. Output includes survey question sets and variations, Python segmentation-trigger and sample-size-calculation logic, SQL for computing NPS and promoter/detractor percentages by segment, a YAML detractor-response and promoter-activation playbook with owners and timelines, dashboard KPI lists for executive and operational views, and a Python trend-analysis function using linear regression to test whether NPS is improving or declining with statistical significance.

-- NPS by customer segment
SELECT 
    customer_segment,
    COUNT(*) as responses,
    ROUND(AVG(nps_score), 2) as avg_score,
    ROUND(
        (SUM(CASE WHEN nps_score >= 9 THEN 1 ELSE 0 END) * 100.0 / COUNT(*)) - 
        (SUM(CASE WHEN nps_score <= 6 THEN 1 ELSE 0 END) * 100.0 / COUNT(*)),
        1
    ) as nps,
    ROUND(SUM(CASE WHEN nps_score >= 9 THEN 1 ELSE 0 END) * 100.0 / COUNT(*), 1) as promoter_pct,
    ROUND(SUM(CASE WHEN nps_score <= 6 THEN 1 ELSE 0 END) * 100.0 / COUNT(*), 1) as detractor_pct
FROM nps_responses 
WHERE survey_date >= CURRENT_DATE - INTERVAL '90 days'
GROUP BY customer_segment
ORDER BY nps DESC;

Analysis code uses Python's scipy.stats.linregress for trend significance and pandas for grouping monthly NPS data; sample-size calculation uses the standard z-score confidence-interval formula. Documented industry benchmarks: SaaS B2B +30 to +40 good and +50 or above excellent, e-commerce +10 to +30 good and +50 or above excellent, financial services +30 to +50 good and +60 or above excellent, and technology +25 to +40 good and +50 or above excellent.

Customer success, CX, and product teams running an NPS program who want a complete framework, question design, distribution triggers, statistical analysis, response playbooks, and benchmarked dashboards, rather than a bare NPS survey with no analysis or action plan.