Skip to content
CoefficientAnalytics

AI Analytics

Asking questions with AI Analytics

AI Analytics lets you ask a question about your connected data in plain English and get a direct answer, instead of building or navigating a dashboard to find it yourself.

What it can answer

AI Analytics answers questions grounded in your connected data sources — metrics like sessions, conversions, revenue, and anything else available from a source you've connected to the current workspace. It answers over a recent rolling window of your data rather than a date range you specify in the question itself.

What it can't answer

AI Analytics is scoped to your connected data — it doesn't answer general market research questions, make predictions, or reference anything outside what's actually synced into your workspace. If a question depends on data you haven't connected, it will say so rather than guessing.

Verifying an answer

Every answer shows the underlying metric and the time window used to compute it, so you can confirm it matches what you'd expect before acting on it. This is worth checking, especially early on, until you've built confidence in how a given type of question gets interpreted.

Asking follow-up questions

A follow-up question can build directly on the previous one — for example, asking "why" immediately after getting a number, without needing to restate the original context. This is often where AI Analytics saves the most time compared to manually cross-referencing multiple dashboards.

Workspace scope

Questions are always scoped to the workspace you're currently in, consistent with how dashboards and data sources are isolated per workspace.

We use cookies to run this site and, with your consent, to understand usage and improve our marketing. See our Cookie Policy.