PromptSharpPrompt LibraryMarketing › Anomaly runbook: the metric moved — check in this order

Analytics & ReportingFREE

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.

The prompt — copy and run it

You are a marketing analyst investigating a metric anomaly. I will describe the metric, the move, and my stack. Produce:

A) An ORDERED RUNBOOK customized to my metric and stack, cheapest-and-most-common causes first: tracking or tagging breakage, reporting-window and timezone artifacts, mix shift (channel, geo, device), seasonality and calendar effects, platform policy or algorithm changes, competitor or external events, and only then genuine performance change — each step with the specific check and what confirming evidence looks like.
B) A HOLDING LINE: the two-sentence status update to send while investigating that informs without committing to a cause.
C) PREVENTION: if the root cause turns out to be instrumentation, the monitor or alert that would catch the next occurrence earlier — described concretely enough to build.

My anomaly: [DESCRIBE: the metric, size and direction of the move, when it started, what changed recently, your analytics stack]

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.

How to use this prompt

  1. Copy the full prompt above with the Copy button.
  2. Add your context. This prompt runs as-is — paste it, then add the specific details, data, or files it should reason over.
  3. Paste into ChatGPT, Claude, or Gemini and run. Read the reality guardrail below before you act on the output.

Why this prompt works

The first explanation in the thread usually wins even when it is wrong. An ordered runbook that starts with instrumentation — where most anomalies actually live — beats narrative-first investigation, and the holding line protects credibility while the facts arrive.

Get a prompt like this every day

The PromptSharp Marketing Brief ships one desk-ready prompt every weekday — free on the web today. Free forever. Today's Marketing issue is live on the web right now — subscribe and we email you the sample issue immediately, then the Marketing daily every weekday as its email edition ships. Unsubscribe anytime.

Subscribe free → Read a sample issue
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?

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

Why does this prompt work?

The first explanation in the thread usually wins even when it is wrong. An ordered runbook that starts with instrumentation — where most anomalies actually live — beats narrative-first investigation, and the holding line protects credibility while the facts arrive.

Related Marketing prompts

Marketing

Segment hypotheses from the data you already have

Everyone wants personas; you have a CRM export and campaign history. Build evidence-based segment hypotheses before anyone invents…

Marketing

Channel plan red-team: find the failure before the spend does

The channel plan is drafted and everyone likes it — which is exactly when it should be red-teamed. Run the adversarial pass before…

Marketing

Pre-launch media QA: the twenty-minute disaster check

The campaign goes live tomorrow. Run the QA that catches the tracking gap, the budget typo, and the missing exclusion before spend…

Marketing

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…

Marketing

Objective to KPI tree: make it measurable before it launches

The objective slide says 'drive awareness and sales.' Before the plan locks, force objectives that can actually be measured — and …

Marketing

Competitor campaign teardown: counter, exploit, or ignore

A competitor just launched loudly and leadership wants a reaction. Decompose what they are doing and whether it deserves one — bef…

Marketing

Brand-voice-locked rewrite with a change log

The draft is fine but it does not sound like the brand — and 'make it more on-voice' is not feedback anyone can act on. Make the e…

All Marketing free prompts

The PromptSharp Marketing Brief page — five full free prompts plus today's issue.

PromptSharp Daily — free

The cross-vertical sampler: one sharp, copy-paste prompt each day, rotating across the roster. Two things in one brief: you get better at AI and prompting, and you see the sharpest prompts from across the network.

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

Better together
Make prompts remember you: Brainfile

Even a sharp prompt starts from zero unless your AI knows you. Brainfile is persistent context — your work, voice, and priorities loaded into every session. Brainfile is the memory; PromptSharp is the playbook. Together they compound — the same prompt gets sharper because it runs on YOUR context.

Set up your brainfile →

Want both? The All-Access + Brainfile annual bundle covers the pair.

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.