Analyze patient experience survey results and plan improvements
Turns CAHPS-style scores and patient comments into the few service drivers worth fixing, with owners and a way to tell if fixes worked.
The prompt
Analyze our patient experience survey results.
Survey type: [e.g. CG-CAHPS, Press Ganey, in-house post-visit survey]
Period and response count: [DETAILS - by location and provider if available]
Scores: [PASTE question-level results, e.g. top-box %, and prior period for comparison]
Patient comments: [PASTE, with names and identifying details removed]
Known operational context: [e.g. staffing shortage, new phone system, construction]
Why this matters to us: [e.g. value-based contract measures, online ratings, provider feedback]
Do this:
1. Summarize the overall picture and the biggest changes from the prior period. Flag any provider or location with too few responses for a fair comparison instead of ranking them.
2. Theme the comments into domains: access and scheduling, phone and communication, wait times, front-desk courtesy, provider communication, billing, facility. Give counts and 2 representative paraphrased comments per theme.
3. Connect themes to scores to identify the 3 likely drivers of overall rating and likelihood to recommend.
4. For each driver, suggest specific operational fixes (e.g. callback standards, wait-time updates in the lobby, teach-back training, billing statement redesign).
5. Note which findings are solid and which need more data.
Return: a one-page summary for leadership, a theme table (Theme | Count | Example | Related score | Fix | Owner), and a 90-day plan with a measurable target for each fix. Do not invent scores or benchmarks; use [ADD BENCHMARK] if comparison data would help.
Highlighted [brackets] are blanks to replace with your own details.
Fill in the blanks and use this promptMore Data & Analysis prompts
What to fill in
- e.g. CG-CAHPS, Press Ganey, in-house post-visit survey
- DETAILS - by location and provider if available
- PASTE, with names and identifying details removed
- e.g. staffing shortage, new phone system, construction
- ADD BENCHMARK
How this prompt is built
This prompt follows the Few-Shot structure (Few-shot prompting). A few-shot prompt includes one or more worked examples of the input and the output you want, so the model can copy the pattern instead of guessing it.
Related prompts
- Find what extra data would strengthen my analysisReviews your analysis and data to pinpoint the missing information that would most improve confidence, and how to get it.
- Identify the leading and lagging indicators for my business or teamSorts your metrics into leading and lagging indicators, links each lead to the outcome it predicts, and fills gaps in early-warning measures.
- Pick the three insights and five numbers my executives needRanks your findings down to the single most important insight, the top three, the five numbers to watch, and the biggest surprise.
- Break down why a number changed between two periodsA driver breakdown and bridge that shows exactly which segments, volume, price, or mix effects caused a metric to move.