PlaybookPrompts

Generate plausible explanations for an unexpected metric movement

Data & Analysis anomaliesanalytics

When a number jumps unexpectedly, the answer matters less than the structured search. This prompt enumerates causes by category so you can rule them out fast.

Prompt 
A metric moved unexpectedly. Help me enumerate causes by category, so I can rule them out fast.

Metric: {{METRIC}}
What happened: {{MOVEMENT}}
When: {{TIMEFRAME}}
What we know is NOT the cause: {{RULED_OUT}}

Produce a ranked list (most likely to least likely) across these categories:
1. INSTRUMENTATION — broken tracking, schema change, time-zone shift, dedup bug.
2. UPSTREAM — change in a marketing channel, traffic source, partner.
3. PRODUCT — feature shipped, A/B test rolled out, UI change.
4. EXTERNAL — seasonality, news event, competitor move.
5. INTERNAL — pricing change, comp plan, support outage.

For each cause, give the cheapest check to confirm or refute it (a query, a screenshot, a Slack thread to read).
Variables to fill in
  • {{METRIC}}
  • {{MOVEMENT}}
  • {{TIMEFRAME}}
  • {{RULED_OUT}}

How to use this prompt

  1. Copy the prompt above (Copy button on the top-right).
  2. Replace each {{VAR}} with your own value. Variables: {{METRIC}}{{MOVEMENT}}{{TIMEFRAME}}{{RULED_OUT}}.
  3. Paste it into one of the recommended tools below.
  4. Iterate: tighten constraints in the prompt if the output is generic.

Why this prompt is structured this way

The prompt is split into explicit steps because LLMs do better when the path is named, not implied. Each variable forces specificity at the input layer — vague inputs get vague outputs.

Heads up: some of the links on this page are affiliate links — meaning we may earn a commission if you sign up after clicking, at no extra cost to you. We only recommend tools we'd put on our own stack. You can see our full affiliate disclosure here.

Pair this prompt with a tool

Claude (Anthropic)

$0/mo (Pro at $20)

Frontier model with long context and strong reasoning.

Claude (Opus / Sonnet / Haiku tiers) is the assistant favored by writers and engineers who care about reasoning quality and tone. 1M token context on Opus.

writingcodinglearning

ChatGPT (OpenAI)

$0/mo (Plus at $20)

The category-defining general-purpose AI assistant.

ChatGPT has the broadest feature surface: image gen, voice, custom GPTs, web browsing, code execution. Often the right default; sometimes beaten on specific tasks by Claude or Perplexity.

writingcodinglearning

Perplexity

$0/mo (Pro at $20)

AI search engine with citations.

Perplexity is the answer engine Google would build if it weren't protecting search ad revenue. Cited answers, follow-up questions, focused source modes.

learningdata

The PlaybookPrompts weekly

One short email per week. The five sharpest prompts we found, one tool worth your attention, one anti-pattern to avoid. Unsubscribe in one click.

Newsletter signup is not configured. Set PUBLIC_NEWSLETTER_USERNAME in the build env.