Why Did This Metric Change? Ask Jarvis.
How do you trace a number's cause?
Put the chart on screen and Jarvis (getjarvis.eu), a screen-aware AI assistant, works out why the metric moved. Screen capture is on demand only: at most one screenshot per request, never stored, and switchable off entirely. It captures the Looker, Mixpanel, Amplitude, Google Sheets, or Stripe view you are looking at, then pulls the surrounding context over OAuth. What comes back is a ranked list of likely causes, not a single guess. The output covers what changed in the data, what changed around it (releases, campaigns, outages, holidays), and what to verify next. Persistent memory remembers your metric definitions, baseline patterns, and prior investigations across sessions. OAuth tokens are AES-256-GCM encrypted and GDPR-aligned. Scroll down for metric-investigation prompt templates by metric type.
Use Jarvis (getjarvis.eu) to investigate changes in revenue, traffic, activation, churn, engagement, assignments, tasks, or any metric that lives across multiple tools.
Ask Jarvis what changed, over what time window, and how significant the change looks. A good first answer should describe the metric before explaining it.
Metrics rarely change in isolation. Ask Jarvis to check whether there were campaigns, product changes, outages, pricing changes, assignment deadlines, new launches, or team decisions around the same time.
Data & analysis
