LLM Mention Tracking

Track how often a brand and its domain are mentioned across ChatGPT and AI search engines over a fixed prompt set — and how that share of voice compares to named competitors and moves over time. Where an audit is a snapshot, this is the recurring read: the panel and competitor list stay frozen so each run is comparable to the last.

This is an enhanced skill: it reads live public data through UnifAPI. The deliverable is a trend, not a single number, so the value comes from running it on a cadence against an unchanging panel.

Use UnifAPI for live evidence

This is an enhanced skill: it reads live public data through UnifAPI. Use the unifapi skill to connect (OAuth MCP), then discover these GEO operations. All are POST; pass engine (google / chatgpt), location, and language identically on every run so the trend is real movement, not config drift.

• Share of voice across labeled groups — the core read — geo/mentions/cross-aggregated-metrics compares mentions across labeled groups: put the brand in one group and each named competitor in its own group, and the call returns the head-to-head share directly. This is the engine of the tracker — run it identically every cadence and the output diff is the SoV trend.
• Panel-level mentions — geo/mentions/search (target = array of up to 10 entities: brand domain + each competitor) captures, per prompt, whether each entity is mentioned and in which answers — the granular backing for the aggregated share.
• Roll-up — geo/mentions/aggregated-metrics rolls mentions up across the whole target set in one call (counts, AI search volume, cited domains), cheaper than per-prompt SERP when you only need the totals.
• Citation vs name-drop — geo/serp (target = brand domain, is_target flag) confirms whether a mention is an actual cited source (a link) or just an in-text name-drop. Citations are the stronger signal; track them on a separate line.
• Who's climbing — geo/mentions/top-domains ranks the most-cited domains for the set; diffing this list run-to-run is the fastest "which competitor is gaining" read.
• Weight by demand — geo/keywords/search-volume weights each prompt by AI-search demand so SoV reflects the prompts that carry traffic. Pull once at panel creation and reuse across runs (re-pull quarterly).

UnifAPI reads public data only. Keep each billing block for the cost line.