# Expressions {% hint style="info" %} NLP sound unfamiliar to you? Make sure you have a look at our detailed [Natural language processing ](/nlp/natural-language-processing-nlp.md)page. {% endhint %}

## Add expressions **Expressions** are the sentences or phrases that customers use to communicate their intent to the chatbot. There are two methods to add expressions to your intents: ### Manual entry 1. Go to your **Intent** tab. 2. Enter a new expression on the input filed. 3. Click **enter** or **+**.

### Generate expressions If you'd like to accelerate the process, you can make the most of Large Language Models (LLM) to generate expressions automatically. To generate expressions using AI: 1. Access the intent you've created. If there are no existing expressions, the name and description of the intent will be used as a prompt for expression generation. 2. Click **Generate Expressions**. The chatbot will provide you with up to 5 suggested expressions based on the provided prompt. 3. Select the ones that you want to keep. 4. Click **Add Selected**.

## Add contextual entities to your expressions To add [contextual entities](/nlp/natural-language-processing-nlp/detect-information-with-entities/contextual-entities.md) to your expressions: 1. As you write expressions, use the '@' symbol to indicate the presence of an entity. 2. You can either create a new contextual entity tag on the spot or select from existing contextual entity tags, depending on your chatbot's predefined contextual entities.

3. To add values to your selected entity, simply click on the entity tag. This will open a modal where you can view or add new values associated with that entity.

--- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://docs.chatlayer.ai/navigation/natural-language-processing-nlp/expressions.md?ask= ``` The question should be specific, self-contained, and written in natural language. 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.