Agency-wide: severity × MRR across every client, one inbox.
All-clients meta-view that runs every per-client alert workflow in parallel and ranks the output by severity × MRR. The 'anything weird across my 30 clients?' inbox.
4-step composite. Every tool call is logged for the tracked_id audit.
Every per-client alert workflow (5, 6, 15, 20, 31 + sentiment + drift) runs across the full book in parallel.
Every anomaly is weighted by client MRR to bias the inbox toward revenue-impacting clients.
Click any row → opens the client's cockpit with the anomaly diagnosis and the triggering datapoints pre-loaded.
Bulk-assign and bulk-queue the recommended workflow chain across selected anomalies.
Each datasource has a provenance chip on the live dashboard, so you always know whether a number came from a live MCP call, a cached snapshot, or a fallback.
Citations, share of voice, sentiment, search-query fan-out, prompt suggestions.
AI bot crawl activity (GPTBot, ClaudeBot, PerplexityBot, OAI-SearchBot, Google-Extended).
Per-URL coverageState, canonical conflicts, robots, render, rich-result eligibility.
Impressions, clicks, average position by query and page.
Sessions, engagement, conversion, revenue, segmented by canonical AI source.
Per-URL GEO readiness score, missing schema, chunkability hints.
You'll get an invite when we open the next batch, plus one short email when we ship a new feature page. No drip campaign, no spam.
Early-access invites go out in small batches. Unsubscribe anytime.