Skip to main content
Analytics is the multi-execution reporting view for an experiment. Use it when you want to see how visibility or sentiment changed across runs — not just the latest snapshot. Navigate to Reporting → Analytics in the sidebar, then select an experiment. For Google Search Console, Google Analytics, and first-touch survey data, use Reporting instead.

​
Analytics vs experiment results

​
Dashboard tabs

After you open an experiment, the analytics dashboard includes:
  • Overview — KPIs, top movers, source concentration, category performance
  • Trends — charts across executions
  • Model compare — visibility experiments only
  • Sources — citation mix, domains, tracked URLs
  • Themes — sentiment experiments only; clustered pros and cons on a 3D/2D map, with aspect, modifier, and intensity filters
  • Insights — auto-generated insight cards

​
Filters and baselines

Use the filter bar to narrow by:
  • Models
  • Categories
You can also toggle execution sanitization to include only executions where every active model returned at least one query result. On Overview, choose a baseline comparison:
  • Default — compare to the previous execution
  • Previous — explicit previous-execution baseline
  • First — compare against the first successful execution

​
Themes

On sentiment experiments, the Themes tab groups similar pros and cons into clusters so large runs stay readable. If the map is empty, click Sync themes. That embeds missing phrases and clusters similar points — needed once for older runs. Use Theme filters to narrow phrases by Aspect, Modifier, and Intensity. Filters apply to the current Pros or Cons polarity — switch Pros/Cons to filter the other side. A phrase must match every dimension you set (for example, both an aspect and an intensity). Selecting every option in a dropdown is the same as leaving that dimension unfiltered. Clear filters removes all constraints. Filters update the cluster map, top theme lists, and introduced themes. When Cons is selected, they also apply to the Cons per theme chart and Watched cons over time. Theme counts show matching phrases, so mild and moderate versions of the same theme appear as separate map points. If nothing matches, the map says No clusters match these filters. The Theme cluster map opens in 3D by default. Drag to rotate; the same color means the same cluster. Hover a point to read the full topic and phrase. Switch to 2D to pan (drag) and zoom (Shift+drag, or the zoom controls). Use Table to list the same phrases by cluster and topic.
  • Pros / Cons — choose which polarity the map and filters apply to
  • Outliers — off by default; turn on to include phrases that did not join a cluster
  • Cons per theme — when Cons is selected, a bar chart shows how many unique con phrases sit in each cluster theme

​
KPI bands

Visibility experiments surface metrics such as overall visibility, visibility trend, winning categories, and at-risk categories. Sentiment experiments surface an Overall rating (the plurality of Positive / Neutral / Negative labels), Negative Categories, and brand citation share. Each response is labeled Positive if the score is 3 or higher, Neutral if it is 0 up to but not including 3, and Negative if it is below 0.

​
Empty states

  • No Execution Data — run at least one successful execution before analytics can load
  • Unable to Load Analytics — retry or confirm the experiment still exists

Reading results

Interpret a single execution’s visibility or sentiment results.

Insights Agent

Ask natural language questions about experiment data.

Scheduling

Keep analytics fresh with recurring executions.

Experiments

Create and manage visibility and sentiment experiments.

Reporting

Review Search Console, Google Analytics, and first-touch survey data.