Dashboard overview

The Overview is your workspace's home screen: a single rolling window summarised as five KPI scorecards, a content-coverage tile, trend and split charts, monitor health, and top movers. Every card is a doorway into the full page behind it.

What it does

Overview pulls one window of collected runs into a set of at-a-glance panels:

• Five KPI scorecards — Visibility, Share of Voice, Citation Share, Sentiment, and Estimated impressions — each with its current value and a period-over-period delta.
• A content-coverage tile showing how much of your prompt set you actually rank for.
• A multi-metric trend chart with a prior-window overlay, so this window is drawn against the one before it.
• A share-of-voice split (you versus your competitor set) and an engine split (where your presence comes from).
• Monitor health, plus top movers, top sources, and top pages.

Everything on the screen is computed from the same window, so the scorecards and the charts always agree.

How to use it

• Filter by engine. Engine chips narrow every panel at once. Only engines that have collected data show a chip — an engine you don't track never appears as an empty option.
• Toggle "Category prompts only." This excludes prompts that name you or a named rival, leaving the honest category view — how you show up when nobody put your name in the question.
• Spot "read but not named." On the trend card titled "You vs. competitors", switch to the Visibility view. From day two, a dashed "your site cited" line is overlaid on the solid line. The solid line is how prominently answers name you; the dashed line is how often they cite your site. When the dashed line runs above the solid one, AI assistants are reading your site but not saying your name — a direct signal for your content and PR work.
• Read the first-run banner. On day one, a cadence-honest banner explains that the window is still filling, so you don't misread a partial window as a low score.
• Follow a card. Every scorecard and list deep-links to its full page — Prompts, Competitors, Sources, Monitors.
• Generate a report. The "Generate report" button opens the client report builder under /reports.

How it's computed

The base scope is the search-grounded engines only (blended), unless you apply an engine filter — then the panels follow that engine. The delta on every scorecard compares the current window against a prior window offset by the same number of days.

• Visibility is scored 0–100 and shown to one decimal.
• Share of Voice uses per-entity run-presence counts — runs that mention an entity at least once — over the total of your brand plus all competitors. Its delta is a point difference (percentage points), not a percent change, because it is a share.
• Citation Share and Sentiment show an em-dash when null — there is nothing to average yet.
• Estimated impressions = the sum, across prompts, of presence_rate × the prompt's volume band. It is an em-dash when demand is unmeasured, never a fabricated count.
• Content coverage = covered prompts ÷ prompts with at least three runs; null renders as an em-dash.
• Top movers are the top five prompts by absolute visibility change in the window.

A few window and honesty rules shape what you see:

• The header reads "Day N of collection" until the window fills.
• Daily series drop null days rather than zero-filling them, so a gap never draws a false dip.
• A metric built from fewer than five runs carries a low-confidence flag.
• Monitors are marked stale after 36 hours without a run.

Limits

• There is no page-level plan gate on Overview.
• The data horizon is 56 days — windows cannot reach further back.
• Your remaining prompt quota is shown by the quota meter in the sidebar.

Related

• Prompts — the tracked-prompt portfolio behind the movers.
• Competitors — the full share-of-voice leaderboard.
• Sources — the domains behind top sources.
• Monitors — the sampling configs behind monitor health.
• Reports — the client report the "Generate report" button opens.
• Overview metrics — the definitions behind each scorecard.
• Data honesty — why null values render as em-dashes.
• API / MCP: GET /api/v1/overview and the get_overview MCP tool — see the Resource reference and MCP server.