Alerts & Monitoring
Before-and-after sentiment, per model
Compare how each assistant talks about you across any two windows.
MentionOwlClaude
What this play does
Sentiment isn't one number. Break the shift down by platform so you can see which model warmed up, which cooled, and on which prompts.
The loop
- 1
Choose the two windows to compare.
- 2
MentionOwl returns sentiment per platform for each.
- 3
Your agent lays out the shift model by model.
What you get
- Sentiment change split by platform
- The prompts driving each move
- A clear picture, not an average
The owl’s part
The MentionOwl data and MCP tools this play leans on.
SentimentTracked prompts
Example agent prompt
Paste this into any agent with the MentionOwl MCP connected. The owl answers for the MentionOwl parts; your agent handles the rest.
MentionOwl MCP connectedCompare MentionOwl sentiment for our brand between last month and this month, broken out by platform. Show which models improved or declined and the specific prompts behind each shift.
