✍️ Writing

Report Writing Prompt: Findings and Summary From Your Data

Turn your pasted numbers and notes into an answer-first report: executive summary, findings with the math shown, recommendations with owners, and data gaps.

0.0
0Reviews
P
October 23, 2026

Prompt

Act as a business report writer who turns raw numbers and notes into an answer-first report that a busy reader can act on. You check every figure against the data I paste, show the math for any percentage or change you state, and label causes as likely or confirmed.

Inputs:
- The reader and what they will decide after reading: [Audience]
- The one question this report must answer: [ReportQuestion]
- The data: tables, monthly figures, survey counts, pasted as text: [Data]
- Context and observations that explain the numbers (launches, staffing, outages, policy changes): [ContextNotes]
- Report type and length (one-page memo, monthly report, incident report, board update): [ReportTypeAndLength]

Generate:
1. Executive summary: 3 to 4 sentences that answer ReportQuestion first, then the biggest number behind the answer, then the main recommendation.
2. Key figures table: metric, each period, change, change in percent. Show the calculation for every derived number in a "Math" line under the table.
3. Findings: 3 to 5 findings, each one sentence of fact from Data, one sentence of meaning, and a label: confirmed by the data, or likely (based on ContextNotes, not proven).
4. Recommendations: one per finding that needs action, with a suggested owner role, a first step, and the metric that would show it worked.
5. Gaps: what the data cannot answer and the exact data that would settle it.
6. A subject line or report title that states the answer, not the topic.

Rules:
- Every number must come from Data or from math on Data. Round percentages to one decimal place.
- Do not invent benchmarks, targets, or industry averages.
- Plain words, short sentences, no filler such as "in today's landscape".

Instructions

Paste the prompt into ChatGPT, fill the brackets, and paste your data as plain text or a small table. Check the Math line against your source before sharing. Only figures from your data should appear in the report.

Generated Output

This image was generated using the prompt above.

Report Writing Prompt: Findings and Summary From Your Data - Result

Examples

Example Input

Audience: Hana Kim, VP of Customer Experience; she will decide Q4 support staffing and fixes
ReportQuestion: Why did customer satisfaction drop in Q3, and what should we fix first in Q4?
Data:
Tickets: July 1,240; August 1,410; September 1,655
Billing tickets: August 310; September 520
Median first response time (hours): July 3.1; August 3.8; September 5.2
CSAT: July 91%; August 89%; September 84%
ContextNotes: new pricing launched September 2; one support agent left August 15 and was not replaced; the help center article on invoices was last updated in March
ReportTypeAndLength: one-page memo

Example Output

TITLE: Q3 CSAT fell 7 points as billing tickets jumped after the pricing change

1. EXECUTIVE SUMMARY
CSAT fell from 91% in July to 84% in September, and the drop lines up with the September 2 pricing launch. Billing tickets rose by 210 from August to September, which is about 86% of all the new ticket volume. At the same time, median first response slowed from 3.1 to 5.2 hours with one fewer agent. Fix billing questions at the source first, then restore response time.

2. KEY FIGURES
Metric | Jul | Aug | Sep | Jul to Sep
Tickets | 1,240 | 1,410 | 1,655 | +415 (+33.5%)
Billing tickets | n/a | 310 | 520 | Aug to Sep +210 (+67.7%)
Median first response (h) | 3.1 | 3.8 | 5.2 | +2.1 (+67.7%)
CSAT | 91% | 89% | 84% | -7 points
Math: 1,655 - 1,240 = 415; 415 / 1,240 = 33.5%. 520 - 310 = 210; 210 / 310 = 67.7%. Aug to Sep total change 1,655 - 1,410 = 245; 210 / 245 = 85.7%. Non-billing tickets: Aug 1,410 - 310 = 1,100; Sep 1,655 - 520 = 1,135; +35 (+3.2%). 5.2 - 3.1 = 2.1; 2.1 / 3.1 = 67.7%.

3. FINDINGS
F1. Billing drove the September increase. Billing tickets grew 210 while all other tickets grew only 35. Confirmed by the data.
F2. The pricing launch is the likely trigger. The billing jump starts the month pricing changed, and the invoice help article predates it. Likely, not proven.
F3. Response time slowed by 2.1 hours. Fewer agents and more tickets both push this up. Likely, based on ContextNotes.
F4. CSAT fell each month, with the biggest drop (5 points) in September. Confirmed by the data.

4. RECOMMENDATIONS
R1 (F1, F2). Owner: support content lead. First step: update the invoice help article for the new pricing this week. Measure: billing tickets per week.
R2 (F2). Owner: billing product manager. First step: tag 50 September billing tickets by reason to find the top two confusions. Measure: share of billing tickets with those reasons.
R3 (F3). Owner: support manager. First step: decide on backfilling the open agent role. Measure: median first response back under 3.8 hours.

5. GAPS
- No July billing figure, so the billing trend before August is unknown. Need: billing ticket count for July.
- CSAT is not split by ticket type. Need: September CSAT for billing versus other tickets to confirm billing caused the drop.
- No data on whether customers read the help article. Need: article views for September.

6. SUBJECT LINE
"Q3 CSAT: billing confusion after the pricing change is the main cause; fix the invoice article first" 

Reviews (0)

Please login to leave a review.
Loading reviews...