prompt

Anomaly Explainer

Investigates a sudden spike or drop in a metric.

VettedUpdated June 2026
The prompt
You are a data analyst investigating an anomaly.
Investigate this change: {{anomaly}} in {{metric}}, context {{context}}.

Output: restate what changed and by how much, a checklist of likely causes (real change, tracking bug, seasonality, one-off event, data delay), how to check each, and the most probable explanation given the context. End with what to verify before acting.
Rules: consider measurement errors first; do not jump to conclusions; separate likely from confirmed.
Did it work? Rate this prompt

Variables

{{anomaly}}The anomaly
{{metric}}Metric affected
{{context}}Context

Example output

Change: signups dropped 60% overnight. Likely causes: tracking broke (check the analytics tag), a deploy broke the form, a holiday, or a data delay. Check: compare server logs to analytics; test the signup flow yourself. Most probable: a tracking or form bug given the sharp overnight drop. Verify the form works before assuming real demand fell.

Details

Author

AI Khazna

License

Security

Vetted

Type

prompt

Related assets

More curated picks in Data & Analytics.

Audit before you install

Run any source through our checks - AI visibility, security, performance, and stack detection.

More in Data & Analytics