DocsMetrics
Metrics overview
The six core metrics MentionFlow computes, the rules they all share — windows, denominators, confidence, and null handling — and where to read each one.
Every number in MentionFlow comes from the same small set of metric functions, so a value means the same thing wherever it appears — a scorecard, a table, a report, or the API.
The six core metrics
| Metric | Scale | Answers the question |
|---|---|---|
| Visibility | 0–100 | How prominently do engines mention you? |
| Share of Voice | 0–100% | Of all brand mentions, how many are yours? |
| Presence rate | 0–1 | In what share of answers do you appear at all? |
| Average position | rank (1 = best) | When you appear, how early are you mentioned? |
| Citation share | 0–1 | Of cited answers, how many cite your domain? |
| Sentiment | 0–100 | When you're mentioned, how positive is the tone? |
Rules every metric shares
- The window. Metrics are computed over a rolling window that anchors at your newest collected day, not the wall-clock "today". The dashboard default is 7 days (also 14, 28, or a custom range up to 56).
- The denominator is every run in the window. A run where you weren't mentioned counts as a zero for visibility and presence — absence is data, not a missing row. The exact denominator for each metric is on its page.
- Blending. Headline metrics — Share of Voice included — blend only the eight search-grounded engines so a knowledge-only engine's empty citations can't distort them, with one deliberate exception: a monitor card includes the engines it collected. See Data honesty.
- Confidence. A metric computed from fewer than five runs carries a low-confidence flag.
- Null is not zero. When a metric has no data to compute — no citations yet, no scored mentions — it is null and renders as an em-dash, never a fabricated
0. See Data honesty.
Versioning
The definitions on these pages are METRICS_VERSION = 1. If MentionFlow ever changes how a metric is computed, it bumps that version and annotates the change on charts rather than silently altering your history. The API exposes these same metrics with the same scales.
Related
- The full derivation of engine sampling and demand tiers: Methodology.
- How these appear in the API: API conventions and the Resource reference.
- The daily series behind the charts, over the API:
GET /api/v1/metrics/history(also theget_metrics_historyMCP tool).