Skip to main content
Suggestions analyze your conversations and surface questions your AI agent failed to answer. The system clusters similar questions together, matches them against your existing knowledge sources, and categorizes each cluster so you know exactly what to fix. Open Suggestions to see your pending clusters.

​
How it works

  1. Extraction. The system scans conversations from the last 90 days and identifies questions that the AI couldn’t answer or answered incorrectly.
  2. Clustering. Similar questions get grouped together. Each cluster shows a canonical question, the number of occurrences, and how many conversations it affected.
  3. Categorization. Each cluster receives an issue type that tells you what kind of fix it needs:
Issue typeMeaningWhat to do
Missing contentYour knowledge base lacks the answerAdd a Snippet, document, or Search Table
Can’t read customer dataThe AI needs to look up data in an external systemAdd a Toolbox, MCP Server, or Unitool
Can’t write customer dataThe AI needs to perform an action in an external systemAdd a Toolbox, MCP Server, or Unitool
  1. Knowledge matching. The system checks whether your existing knowledge sources already contain a relevant answer and flags the match quality: identical, partial, or unrelated.

​
Learning from human agents

In ticketing channels (Zendesk, Salesforce), human agents often resolve the same questions your AI couldn’t answer. Suggestions captures these human-provided answers and includes them in the cluster. This means you can see both what the customer asked and how your team answered it, giving you a ready-made answer to add to your knowledge base.

​
Reviewing suggestions

Each suggestion cluster has three states:
StatusMeaning
PendingNew cluster, not yet reviewed
AcceptedYou plan to act on this
DismissedNot relevant or already addressed
Filter by issue type to focus on one category at a time. Click a cluster to see all related conversations, the canonical question and answer, and the knowledge source match.

​
FAQ

Yes. When human agents answer questions in your ticketing system, Suggestions captures those answers and surfaces them alongside the original questions. You can then add these answers as Snippets or documentation sources so the AI handles similar questions autonomously in the future. The AI doesn’t learn automatically from tickets. You review the suggestions and decide what to add to the knowledge base.
Suggestions analyze conversations from the last 90 days by default.
The system processes new conversations and updates suggestions every 6 hours.