> For the complete documentation index, see [llms.txt](https://docs.ngsurvey.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.ngsurvey.com/ai-suite/smart-columns/smart-works/labels.md).
# Labels
The label smart work allows you to dynamically define label categories that will be used to evaluate and categorize your respondents text entry contents. Each respondent text entry will be evaluate to see if it matches one or more labels that you have defined. Each label that matches the text entry content will be kept as a value of the smart column.
Using labels you can easily and automatically categorize your respondent answers to make grouping and filtering easier during your data analysis.
## 🔅 Label properties
* **`Source answer column`**is the column of your respondents dataset that will be used as source for label categorization.
* **Labels** label of your category. You can add multiple labels. If the source answer can be categorized by any of the labels the smart column value will be assigned that label. If no category can be matched based on the labels ngSurvey will assign a default "unknown" label value.
* **`Number of labels to include`** maximum number of labels to include.
{% hint style="info" %}
Labeling is not a text comparision, based on on the respondent text entry it will evaluate the text to see if any of the labels that you have specified could be used to categorize that entry with it.
{% endhint %}
Below an example of a smart column that categorize a review entry
Based on the respondent review text we can see that it will automatically assign the right category to the smart column that we have created.
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.
Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:
```
GET https://docs.ngsurvey.com/ai-suite/smart-columns/smart-works/labels.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
