> For the complete documentation index, see [llms.txt](https://docs.n8n.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.n8n.io/build/integrate-ai/ai-examples/use-ai-for-parameters.md).
# Use AI for parameters
When configuring tools[^1] connected to the Tools Agent, many parameters can be filled in by the AI model itself. The AI model will use the context from the task and information from other connected tools to fill in the appropriate details.
There are two ways to do this, and you can switch between them.
## Let the model fill in the parameter
Each appropriate parameter field in the tool's editing dialog has an extra button at the end:
On activating this button, the [AI Agent](#user-content-fn-2)[^2] will fill in the expression for you, with no need for any further user input. The field itself is filled in with a message indicating that the parameter has been defined automatically by the model.
If you want to define the parameter yourself, click on the 'X' in this box to revert to user-defined values. Note that the 'expression' field will now contain the expression generated by this feature, though you can now edit it further to add extra details as described in the following section.
{% hint style="warning" %}
Activating this feature will overwrite any manual definition you may have already added.
{% endhint %}
## Use the `$fromAI()` function
The `$fromAI()` function uses AI to dynamically fill in parameters for tools connected to the [Tools AI agent](/integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.agent/tools-agent.md).
{% hint style="info" %}
**Only for tools**
The `$fromAI()` function is only available for tools connected to the AI Agent node. The `$fromAI()` function doesn't work with the [Code](/integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.toolcode.md) tool or with [other non-tool cluster sub-nodes](/integrations/builtin/cluster-nodes/sub-nodes.md).
{% endhint %}
To use the `$fromAI()` function, call it with the required `key` parameter:
```javascript
{{ $fromAI('email') }}
```
The `key` parameter and other arguments to the `$fromAI()` function aren't references to existing values. Instead, think of these arguments as hints that the AI model will use to populate the right data.
For instance, if you choose a key called `email`, the AI Model will look for an email address in its context, other tools, and input data. In chat workflows, it may ask the user for an email address if it can't find one elsewhere. You can optionally pass other parameters like `description` to give extra context to the AI model.
### Parameters
The `$fromAI()` function accepts the following parameters:
| Parameter | Type | Required? | Description |
| -------------- | ------ | --------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `key` | string | ✅ | A string representing the key or name of the argument. This must be between 1 and 64 characters in length and can only contain lowercase letters, uppercase letters, numbers, underscores, and hyphens. |
| `description` | string | ❌ | A string describing the argument. |
| `type` | string | ❌ | A string specifying the data type. Can be string, number, boolean, or json (defaults to string). |
| `defaultValue` | any | ❌ | The default value to use for the argument. |
### Examples
As an example, you could use the following `$fromAI()` expression to dynamically populate a field with a name:
```javascript
$fromAI("name", "The commenter's name", "string", "Jane Doe")
```
If you don't need the optional parameters, you could simplify this as:
```javascript
$fromAI("name")
```
To dynamically populate the number of items you have in stock, you could use a `$fromAI()` expression like this:
```javascript
$fromAI("numItemsInStock", "Number of items in stock", "number", 5)
```
If you only want to fill in parts of a field with a dynamic value from the model, you can use it in a normal expression as well. For example, if you want the model to fill out the `subject` parameter for an e-mail, but always pre-fix the generated value with the string 'Generated by AI:', you could use the following expression:
```javascript
Generated by AI: {{ $fromAI("subject") }}
```
### Templates
You can see the `$fromAI()` function in action in the following templates[^3]:
* [Angie, Personal AI Assistant with Telegram Voice and Text](https://n8n.io/workflows/2462-angie-personal-ai-assistant-with-telegram-voice-and-text/)
* [Automate Customer Support Issue Resolution using AI Text Classifier](https://n8n.io/workflows/2468-automate-customer-support-issue-resolution-using-ai-text-classifier/)
* [Scale Deal Flow with a Pitch Deck AI Vision, Chatbot and QDrant Vector Store](https://n8n.io/workflows/2464-scale-deal-flow-with-a-pitch-deck-ai-vision-chatbot-and-qdrant-vector-store/)
[^1]: In an AI context, a tool is an add-on resource that the AI can refer to for specific information or functionality when responding to a request. The AI model can use a tool to interact with external systems or complete specific, focused tasks.
[^2]: AI agents are artificial intelligence systems capable of responding to requests, making decisions, and performing real-world tasks for users. They use large language models (LLMs) to interpret user input and make decisions about how to best process requests using the information and resources they have available.
[^3]: n8n templates are pre-built workflows designed by n8n and community members that you can import into your n8n instance. When using templates, you may need to fill in credentials and adjust the configuration to suit your needs.
---
# 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 dynamically by asking a question.
Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:
```
GET https://docs.n8n.io/build/integrate-ai/ai-examples/use-ai-for-parameters.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.
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.