executive finance user risk: medium

Monthly MRR Churn Report Generator

Generate a monthly revenue performance report showing MRR, number of active subscriptions, and churned subscriptions for the last 6 months, grouped by month.

Policy sensitive
Human review

PROMPT

Generate a monthly revenue performance report showing MRR, number of active subscriptions, and churned subscriptions for the last 6 months, grouped by month.

EXPECTED OUTPUT

Format

table

Constraints

grouped by month
show MRR
show number of active subscriptions
show churned subscriptions
cover last 6 months

SUCCESS CRITERIA

Show MRR grouped by month
Show number of active subscriptions grouped by month
Show churned subscriptions grouped by month
Cover the last 6 months

FAILURE MODES

Using wrong time period
Omitting one or more required metrics
Failing to group by month
Generating data without source information

CAVEATS

Dependencies

Requires revenue and subscription data for the last 6 months

Missing context

Data source or sample dataset
Output format details
Current date or absolute date range
Definitions or calculation methods for metrics

Ambiguities

Data source for MRR, active subscriptions, and churned subscriptions not specified.
Output format (e.g., table, chart, text) not specified.
Exact definitions of MRR, active, and churned subscriptions not provided.
'Last 6 months' relative to unspecified current date.

QUALITY

OVERALL: 0.60
CLARITY: 0.85
SPECIFICITY: 0.75
REUSABILITY: 0.30
COMPLETENESS: 0.50

IMPROVEMENT SUGGESTIONS

Specify data source: 'Using the following dataset: [insert data]' or 'Assume standard subscription data'.
Define output format: 'Output as a markdown table with columns: Month, MRR, Active Subs, Churned Subs'.
Add parameters for reusability: 'Generate report for last {N} months using {data_source}'.
Clarify metrics: 'MRR = Monthly Recurring Revenue, active = paying subs at month-end, churned = subs cancelled that month'.

USAGE

Copy the prompt above and paste it into your AI of choice — Claude, ChatGPT, Gemini, or anywhere else you're working. Replace any placeholder sections with your own context, then ask for the output.