/platform/{chatbotId}/deep-search lets you find conversations using natural language queries that match by meaning rather than exact keywords. This is useful for discovering patterns and themes that traditional keyword search would miss.
How it works
Deep search uses vector embeddings to understand the semantic meaning of your query and match it against conversation content. Instead of looking for exact word matches, it finds conversations that are conceptually related to your search.Using deep search
Set a date range (optional)
Click the date range button to narrow results to a specific time period. Defaults to This month.
Enter a natural language query
Type a description of what you’re looking for in the search box. Be descriptive — semantic search works best with natural language.
Example queries
| Query | What it finds |
|---|---|
| ”users asking about pricing” | Conversations where users discuss costs, plans, or billing |
| ”billing issues” | Conversations about payment problems, invoice questions, refunds |
| ”frustrated about wait times” | Conversations expressing dissatisfaction with response speed |
| ”wants to integrate with Slack” | Conversations mentioning Slack integration needs |
| ”confused about setup” | Conversations where users struggle with onboarding |
Next steps
Conversations
Browse and filter conversations with column-based filters.
Analytics dashboard
See aggregated trends across all conversations.