Audit AI brand visibility and sentiment
A detailed report on brand mentions across AI engines, including sentiment analysis, share of voice, and competitor comparisons, with strict adherence to statistical rules.
How it works
The agent calls get_me to understand account rules and thresholds. It uses get_visibility to check mention frequency per engine and get_sentiment to analyze framing. It retrieves list_competitors and get_share_of_voice to benchmark performance. The agent must follow the three rules: never average engines, treat null rates as insufficient data (not zero), and interpret empty alerts as no significant change. It presents per-engine data and pooled counts if requested.
Prompt
Paste this into an agent that has the servers below connected. Adjust the names and dates to your own.
Check my account limits. Then report how often ChatGPT named us last month, the sentiment, and our share of voice vs competitors. Did anything change this week?MCP servers it needs
Source
The vendor page this playbook is drawn from, and the passage that supports it.
get_visibility | /visibility | How often does each engine name us.AIMentionTracker MCP documentation