Cee is a multi-agent system, meaning under the hood, it’s composed of a main AI agent and several specialized sub-agents. As a user, you will just interact with “Cee” as a single chat assistant, but it’s helpful to understand how it operates:
- Main Documentation Agent (Cee): This is the primary agent you converse with. Its job is to understand your questions or commands and determine how best to help. It has access to Countly documentation via a safe web search, so it can fetch instructions or explanations from Countly support articles. In essence, this agent serves as an interactive documentation concierge inside Countly.
- Intent Analysis and Orchestration: The main agent also continuously interprets your intent. Based on what you ask, it might decide to:
- Answer directly using documentation (for general questions or guidance), or
- Hand off to a specialized agent if your request coincides with one of these agents' specialty.
- Proactive Suggestions: Another way Cee orchestrates the experience is by suggesting useful actions or feature usage.
In the image above, the user asked about segmenting users, and Cee’s response includes two suggestion buttons: one to explain the Cohorts feature in detail, and another to jump straight into creating a new Cohort. These suggestions help bridge the gap between theory (documentation) and practice (taking action in Countly).
- Context Awareness: Throughout a conversation, Cee remembers the context (within a limit). If you’ve been talking about funnels, it knows to keep that context, so you can ask follow-ups like “How do I add another step to that?” without restating all details. Cee will retain recent messages to maintain continuity.