PromptSharpPrompt LibraryMarketing › Metric dictionary: kill the double-counted number

Analytics & ReportingFREE

Metric dictionary: kill the double-counted number

Two dashboards disagree about 'leads' again — in front of your boss. Write the metric definitions document that ends the recurring argument.

The prompt — copy and run it

You are a marketing data steward writing a metric dictionary. I will list our reporting metrics and known disagreements. Produce:

A) A METRIC DICTIONARY table: metric name, exact definition (including time window, deduplication, and filters), source system, owner, and — where I flagged a disagreement — the known gap between systems.
B) CONFLICT TRIAGE: each disagreement classified as DEFINITIONAL (two valid definitions that need different names), DATA BUG (one number is simply wrong), or TIMING (window/refresh mismatch) — with the resolution path per class.
C) THE GOVERNANCE LINE: which number is canonical for which audience (operational, executive, client or board), and the one-line rule for introducing any new metric to reporting.

My metrics: [PASTE: metrics used in reporting, the system each comes from, the disagreements you have hit, who consumes which report]

Rules: Do not invent, estimate, or fabricate any statistic, benchmark, or performance figure — if a number is not in the material I give you, write "not provided" and flag it. Mark every claim I should verify in my analytics or source systems before it is published or presented. Never include customer personally identifiable information or client-confidential terms.

Why this prompt works

Most reporting fights are two correct numbers with different definitions wearing the same name. Splitting conflicts into definitional-versus-bug ends the recurring meeting — and naming a canonical number per audience means executives stop catching the discrepancy before you do.

Want the daily version?

The PromptSharp Marketing Brief delivers prompts like this every day. Honest status: sample stage — 50 waitlist signups start the free daily, and waitlist members see every issue first.

Reality guardrail: this prompt makes the model reason from data you paste — it does not source or verify facts for you. Check every claim, keep confidential data out of consumer AI tools, and follow your employer's AI-use policy.

Frequently asked

When should I use this prompt?

Two dashboards disagree about 'leads' again — in front of your boss. Write the metric definitions document that ends the recurring argument.

Why does this prompt work?

Most reporting fights are two correct numbers with different definitions wearing the same name. Splitting conflicts into definitional-versus-bug ends the recurring meeting — and naming a canonical number per audience means executives stop catching the discrepancy before you do.

Related Marketing prompts

Analytics & Reporting

Anomaly runbook: the metric moved — check in this order

A KPI spiked or cratered and the channel wants answers now. Work the ordered runbook before anyone ships a theory that sticks.…

Analytics & Reporting

Executive one-pager: 3 numbers, 3 insights, 3 asks

Leadership wants the marketing readout on one page — and every number on that page will be challenged. Compress without losing the…

Analytics & Reporting

Dashboard spec: the minimum set someone actually maintains

The 40-widget dashboard nobody opens needs replacing. Spec the minimum-viable version where every element serves a decision and al…

Campaign Strategy & Briefs

Creative brief builder: from messy kickoff notes to one page

Kickoff happened, the notes are chaos, and creative starts Monday. Get the single-page brief that prevents three rounds of rework.…

All Marketing free prompts

The PromptSharp Marketing Brief page — five full free prompts plus the ladder status.

PromptSharp Daily — free

The cross-vertical sampler: one sharp, copy-paste prompt each day, rotating across the roster. See what each vertical is like before you commit to one.

Double-opt-in. Unsubscribe anytime. No spam, ever.

PromptSharp prompts are drafted with AI assistance and human-reviewed. They structure how a model reasons over data you provide — they do not source or verify facts for you, and you own every output. Nothing here is financial, legal, tax, or investment advice. Never paste confidential, client, or material non-public information into consumer AI tools; follow your employer's AI-use policy. © 2026 PromptSharp.