Track how your brand appears in AI answers across ChatGPT, Gemini & Claude. Measure mention rate, share-of-voice vs competitors, ranking & cited sources — with multi-sample reliability. GEO / AEO visibility data for SEO agencies, brand & PR teams. Pay-as-you-go.
Skipped engines (dead key / out of credit) no longer emit mentionRatePct: 0 — they now carry skipped: true with null metrics, are excluded from the engine count, and aggregates count only engines that produced answers. Found in the field on a live client measurement (an engine reported as "0% mentions" had never been queried).
0.1.16 — 2026-07-28
Graceful engine degradation: a dead / out-of-credit engine key disables that engine for the run with one warning and a summary enginesSkipped entry — no more per-query error rows.
Dotted-brand fix: excerpt AND sentiment now survive brand names with dots ("Uzm. Dt. Şevval Öksüz", "Acme Inc.") via a dot-safe splitter + ±120-char window fallback.
Honest scoring recalibration: citationRatePct is now measured over ALL samples (matches README) and the index's rank/citation components scale with mention rate — 1/10 visibility can no longer score 55 (now ~10). First delta after updating reflects the recalibration.
0.2 — 2026-07-05
Reworked docs to the foXLabs gold standard: API quick-start, full output-field reference (per-prompt + summary), illustrative sample records, JS / Python / Make / MCP integrations, expanded FAQ, troubleshooting and honest limits.
0.1.10 — 2026-07-05
Hardened output handling so an edge-case value can never trip dataset-schema validation.
0.1.9 — 2026-06-27
Resilience fix: API quota/billing-exhaustion errors (HTTP 429 insufficient_quota) are now detected and failed-fast instead of retried as transient rate limits. A depleted engine key is skipped in ~1s instead of wasting ~30s of dead retries per call — keeping runs fast and well within platform time limits.