> Source: https://builder-docs.ema.ai/agent-reference/core/categorize-conversations-and-route > Title: Categorize Conversations and Route Agent # Categorize Conversations and Route Agent The Categorize Conversations and Route agent classifies incoming chat conversations into user-defined categories and routes the workflow down the corresponding branch. It combines deterministic rule-based filtering with LLM classification for flexibility and accuracy. Formerly known as the **Intent Classifier**. ## Use Cases - A chat-based AI Employee needs to handle multiple types of requests (e.g., billing questions, technical support, general inquiries). - You want to route conversations to different workflow branches based on intent. - You need both deterministic keyword matching and LLM-based classification. - You want to let the end user choose when a message could match multiple categories. ## Inputs Input Type Description `chat_conversation` Conversation The chat conversation to classify. The agent considers the most recent messages (see _context window_ below). ## Outputs Output Type Description `category` Category The assigned category name. Each category becomes a named output edge on the GWE canvas, enabling direct branching. ## Configurations Parameter Description Default **Categories** List of category definitions. Each category has a name, description (up to 1,000 characters), and optional example queries and qualification criteria. Required **Fallback category** Category assigned when no rule matches and the LLM cannot confidently classify the message. Defaults to "Fallback" and cannot be changed once set. "Fallback" **Context window** Number of recent messages the agent considers when classifying. Older messages are ignored. 10 **Human collaboration** When enabled, if the agent detects multiple matching categories, it presents the end user with buttons to choose the correct one instead of guessing. Off **Additional instructions** Custom guidance for the LLM classifier (e.g., "Treat refund requests as billing, not complaints"). None ### Configuring Categories Each category in the list supports: - **Name** -- a clear, descriptive label (e.g., "Billing", "Technical Support"). Must be unique within the agent. - **Description** -- tells the LLM when to assign this category (up to 1,000 characters). Be specific: "Questions about invoices, charges, payment methods, or subscription billing" is better than "Billing stuff". - **Example queries** -- sample messages that belong to this category. These help the agent match similar messages, and on exact match the agent assigns the category instantly without calling the LLM. - **Qualification criteria** -- deterministic rules that force a category assignment without LLM evaluation. Requires a [JSON Extractor](/legacy-docs/agent-reference/core/json-extractor) agent connected upstream to supply structured data for rule evaluation. ### How Classification Works 1. **Exact match check:** If the user's message exactly matches an example query, that category is assigned immediately. 2. **Qualification criteria:** If rules are configured and structured data is available from an upstream JSON Extractor, the rules are evaluated. A match assigns the category without calling the LLM. 3. **LLM classification:** If no deterministic match occurs, the agent sends the recent conversation (limited by context window) to the LLM along with your category descriptions and instructions. 4. **Multi-intent handling:** If the LLM detects the message could match multiple categories and human collaboration is enabled, the end user sees clickable buttons to choose. Otherwise, the agent picks the best match. 5. **Fallback:** If no category matches, the fallback category is assigned. ## How to Use This Agent A customer service AI Employee with three intents: ``` chat_trigger -> categorize_conversations_and_route -> [billing] -> search_billing_kb -> respond -> workflow_output -> [technical] -> search_tech_kb -> respond -> workflow_output -> [other] -> general_respond -> workflow_output ``` ## Tips - **Write detailed category descriptions.** The LLM relies on these to distinguish between categories. Vague descriptions lead to misclassification. - **Add example queries** for high-volume, unambiguous intents. Exact matches bypass the LLM entirely, reducing latency and cost. - **Enable human collaboration** for workflows where getting the category wrong is costly (e.g., routing a complaint to sales). The small friction of asking the user to click a button is worth the accuracy gain. - **Use qualification criteria** when you have structured data (from a JSON Extractor) that reliably determines the category -- for example, routing based on a ticket priority field or customer tier. - **Keep the context window at 10** unless your conversations are unusually long. More context means higher LLM cost and can introduce noise from earlier, unrelated parts of the conversation. ## Related Agents - [Categorizer](/legacy-docs/agent-reference/core/categorizer) -- more flexible categorization that works with any input type, not just conversations. - [Text Categorizer](/legacy-docs/agent-reference/core/text-categorizer) -- categorizes plain text rather than conversation objects.