Dashboard Anomaly Investigation Playbook
Investigate sudden metric changes.
The Open buttons send the prompt text as currently shown below to that site only when you click. Fill in the placeholders first.
Create a playbook for a sudden metric change. The metric and the change observed: [METRIC_AND_CHANGE]. Recent releases and events: [RECENT_EVENTS]. Data sources: [DATA_SOURCES]. Walk through the investigation in order: verify the data (tracking change, pipeline delay, duplicates, time zone, definition change); check scope (all users or a segment: platform, country, plan, channel, version); check timing against releases, campaigns, outages, holidays, and competitor events; compare with related metrics (traffic, errors, revenue); form hypotheses and rank them; test with the quickest check first. Return a table: Hypothesis | Evidence for | Evidence against | Check | Result | Next step. Include a communication template for stakeholders (80 words) that states what is known, what is not, and when the next update comes. Add a post-incident note format. Add a checklist for the first 15 minutes, a decision on whether to alert stakeholders (if the change exceeds a set threshold or touches revenue), and a table template for recording each hypothesis and its result.
Fill in before use
Optional: type your details and the prompt above updates. Nothing is saved or sent.
Replace each bracketed placeholder with your own details, then paste into Any AI or another assistant.