Classifier
Description
The Classifier step uses AI to sort input text into categories that you define. To configure this step, you provide a name and a specific description for each category. The AI analyzes the input data and compares it against these descriptions to identify the best match. By understanding the context provided in your descriptions, the step assigns the most relevant category to the input. This process enables automated decision-making and allows you to route information to the correct path in your workflows based on the classification results.
Example using Classifier step: The process automatically monitors incoming emails, classifies them, and routes them to the right team. The process performs the following actions:
- The process monitors xyz@gmail.com, for emails with a specific subject line.
- When a matching email arrives, the Classifier Step analyzes the email’s subject and body.
- It categorizes the email (for example, New Invoice, Payment Query, or Supplier Dispute) and forwards it to the respective team, such as the Accounts team for new invoices. The process efficiently monitored incoming emails, classified them accurately based on content, and routed each email to the appropriate team, ensuring timely and organized handling of queries.
Configurations
| No. | Field Name | Description |
|---|---|---|
| 1 | Step name | Specify a unique name for the step. The name helps you identify the step in the workflow and makes it easier to debug or link it with other steps |
LLM Setting tab
For the LLM field details, click LLM setting
Input tab
| No. | Field Name | Description |
|---|---|---|
| 1 | Source data | Specify the input source data that you want to analyze and classify into your defined categories. This data can include plain text, user queries, email content, document text, or output from previous steps. Press Ctrl + Space to insert a variable or Shift + Space to insert a field. |
| 2 | Additional context | Specify extra instructions or background information to guide the LLM while classifying the source data. Use the field to clarify intent, define classification rules, or provide domain-specific guidance to improve accuracy. Press Ctrl + Space to insert a variable or Shift + Space to insert a field. |
Categories tab
| No. | Field Name | Description |
|---|---|---|
| 1 | Category name | Specify a unique name for the category. This name acts as the label that the step outputs when a match is found. Ensure the name is distinct and meaningful, as this value will be used by subsequent steps in your workflow to route data or trigger specific actions. |
| 2 | Category description | Specify a detailed description of the category. The model uses this text as its primary guide to understand the intent and context of the category. To ensure high accuracy, write clear definitions that distinguish this category from others, effectively teaching the model exactly when to apply this classification to the input data. |
Output tab
Use the Output tab to save the results of the AI Agent's execution into variables. You can reference these field name in later steps of your workflow to use the AI's answer or track usage costs.
| No. | Field Name | Description |
|---|---|---|
| 1 | Category | Specify the variable that stores the identified category name. You can use this variable as input for subsequent steps in your workflow. Note: Based on the user query, the step classifies the data and returns the category name; otherwise, it returns the result as Unmapped. Default value: Category |
| 2 | Total tokens | Specify a field name to track the total number of tokens used during the execution. This value is the sum of both input and output tokens, representing the total processing size of the transaction. Default value: totalTokens |
| 3 | Input tokens | Specify a field name to count the tokens sent to the AI model. This count includes your prompts, system instructions, and any attached files or context used to ask the question. Default value: inputTokens |
| 4 | Output tokens | Specify a field name to count the tokens generated by the AI in its reply. This measures the length of the response or answer provided by the model. Default value: outputTokens |