The Survey Results Analyzer
Why this prompt matters
Teams that manually code open-ended survey responses spend an average of 2-3 full workdays per survey cycle doing it by hand, and rushed manual analysis under deadline pressure frequently misses early attrition signals buried in a handful of written comments — the same signals that show up as a resignation spike two quarters later once it's too late to act.
What we use it for
A People Ops manager just closed a 340-response employee engagement survey across the engineering organization and has 48 hours to present findings to the VP of Engineering before a headcount planning meeting, with only a raw CSV export and no built-in analytics dashboard.
Prompt
<p>Act as a senior people-insights analyst who has spent a decade turning raw survey exports into findings that change how leadership makes decisions.</p><p><strong>Context:</strong> I ran a survey titled [SURVEY NAME/PURPOSE — e.g. "Q3 Employee Engagement Survey"] with [NUMBER] respondents out of [TOTAL POPULATION] invited (response rate). The survey included both closed-ended (rating scale, multiple choice) and open-ended questions. The audience for your analysis is [AUDIENCE — e.g. "the VP of People and the executive team"], and the decision they need to make is [DECISION — e.g. "whether to fund a retention initiative for the engineering org"].</p><p><strong>Task:</strong> Analyze the raw survey data below and produce a findings report that helps the audience make that decision. Do not just describe what the data says — identify what matters most and what to do about it.</p><p><strong>Constraints:</strong><br/>- Report exact percentages and counts, never vague terms like "most" or "many."<br/>- Explicitly flag any finding based on a subgroup smaller than [MINIMUM SAMPLE SIZE — e.g. 15] respondents as low-confidence.<br/>- Distinguish correlation from causation — if two data points move together, say so, but do not claim one caused the other unless the data supports it.<br/>- When coding open-ended responses into themes, report how many distinct responses support each theme, and include 1-2 verbatim quotes (anonymized) per theme.<br/>- If closed-ended and open-ended responses conflict on the same topic, surface the conflict explicitly rather than picking one to report.</p><p><strong>Output Format:</strong><br/>1. <strong>Executive Summary</strong> (2-3 sentences: the single most important finding and its business implication)<br/>2. <strong>Quantitative Breakdown</strong> (key metrics by question, with response rate and any notable subgroup differences)<br/>3. <strong>Qualitative Themes</strong> (3-5 themes from open-ended responses, ranked by frequency, each with supporting quote(s))<br/>4. <strong>Sentiment Analysis</strong> (overall tone breakdown: positive/neutral/negative, and what's driving negative sentiment specifically)<br/>5. <strong>Recommended Actions</strong> (2-4 specific actions, each tied to a finding above, with a suggested owner)</p><p>[PASTE RAW SURVEY DATA HERE — CSV, table, or list of responses]</p>
Result
Executive Summary
Engineering engagement scores dropped from 7.8 to 6.4 (out of 10) this quarter, driven primarily by a sharp decline in perceived career growth (42% rated it 3/10 or lower, up from 18% last quarter) — this is the strongest single predictor of the resignation intent flagged in open-ended responses.
Quantitative Breakdown
- Response rate: 340/410 (82.9%), a strong sample.
- Overall engagement: 6.4/10 average, down from 7.8/10 last quarter (n=340).
- Career growth satisfaction: 42% rated 3/10 or lower (143 respondents), up from 18% (61 respondents) last quarter.
- Manager relationship score held steady at 7.6/10 — this is not where the decline originates.
- Note: the 12-person Platform sub-team scored notably lower (5.1/10 average) but this is a low-confidence finding given the small subgroup size.
Qualitative Themes
1. Lack of promotion clarity (61 mentions) — "I don't know what I need to do to get to senior, and neither does my manager."
2. Increased on-call burden (44 mentions) — "On-call has doubled since the reorg and nobody adjusted expectations."
3. Positive team culture (38 mentions) — "My immediate team is the best part of this job," consistent with the steady manager relationship score.
Sentiment Analysis
58% negative, 27% neutral, 15% positive on open-ended responses overall — a reversal from last quarter's 45% positive. Negative sentiment concentrates almost entirely around career progression and on-call load; sentiment toward direct managers and team culture remains positive, indicating the issue is structural/organizational rather than a management-quality problem.
Recommended Actions
1. Publish clear leveling criteria for senior promotion — People Ops + Eng Leadership, next 30 days.
2. Audit on-call rotation load post-reorg and rebalance — Eng Managers, next 2 weeks.
3. Follow up individually with the 12-person Platform sub-team given its lower score, before drawing org-wide conclusions from that group.
Most "analyze this survey" prompts return an average score and a vague paragraph about themes. That's not useful when the decision on the table is whether to fund a retention program or restructure a team. The Survey Results Analyzer is built to surface what actually changes a decision, and to be honest about what the data can't tell you.
Why this prompt is structured the way it is
The Constraints section is doing the most important work. Requiring exact percentages instead of "most respondents" forces the model to actually engage with the numbers rather than paraphrase them. The instruction to flag any subgroup under a minimum sample size as low-confidence exists because it's extremely easy for an AI — or a human analyst under deadline pressure — to draw a confident conclusion from 8 people and present it with the same authority as a finding based on 300.
The correlation-versus-causation constraint matters more with AI-generated analysis than human analysis, because language models are fluent enough to state a causal claim persuasively even when the data only supports a correlation. Requiring the model to distinguish the two, and to surface direct conflicts between closed-ended ratings and open-ended comments rather than quietly picking whichever supports a cleaner narrative, keeps the output honest.
The Output Format's five sections map directly to what a decision-maker actually needs. "Sentiment Analysis" specifically asks what's driving negative sentiment — not just the percentage — because a negative score with no driver identified isn't actionable. "Recommended Actions" requires each action to tie back to a specific finding above it, which prevents the model from generating generic advice ('improve communication') disconnected from what the survey actually showed.
How to use it well
Fill in the audience and decision fields specifically — an analysis written for a VP deciding on a retention budget looks different from one written for an HR team designing next quarter's survey questions. For recurring survey cycles (quarterly engagement, post-event feedback, customer NPS), save your filled-in version and swap in the new raw data each cycle so you get a consistent report structure to compare quarter over quarter.
Takeaways
The value here isn't compressing data — it's forcing the same discipline a careful human analyst would apply: distinguishing what's statistically solid from what's a weak signal, tracing sentiment to its actual driver, and tying every recommendation to specific evidence. Use it whenever a decision depends on survey data and you don't have days to manually code the open-ended responses.