> For the complete documentation index, see [llms.txt](https://learn.coremodels.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://learn.coremodels.io/user-guides/neo-ai-agent.md).

# Neo AI Agent

## Capabilities

### Reading Data

Neo can retrieve and explore your CoreModels project's schemas, and entities through conversational queries.

### Creating Data

Neo can create new schemas and entities in CoreModels based on your instructions.

### File Attachment

Neo supports file attachments in conversations, allowing you to upload documents for context or reference during your interactions.

***

## Example Prompts

### Creating Data

This example shows Neo creating a Person schema in CoreModels from an uploaded (attached) JSON-LD file.

***

📎 **File attached:** person schema.txt

```json
{
  "@context": "https://schema.org",
  "@type": "Person",
  "@id": "https://example.com/people/jane-doe",
  "name": "Jane Doe",
  "givenName": "Jane",
  "familyName": "Doe",
  "alternateName": "J. Doe",
  "birthDate": "2005-08-17",
  "gender": "Female",
  "email": "mailto:jane.doe@example.com",
  "telephone": "+1-555-123-4567",
  "url": "https://example.com/jane-doe",
  "image": "https://example.com/images/jane.jpg",
  "sameAs": [
    "https://www.wikidata.org/wiki/Q123456",
    "https://www.instagram.com/janedoe"
  ],
  "address": {
    "@type": "PostalAddress",
    "addressLocality": "New York",
    "addressRegion": "NY",
    "addressCountry": "US"
  }
}
```

> **User**
>
> create the schema found in the attached file inside coremodels.

> **Neo**
>
> I'll help you create the Person schema from the attached file in CoreModels. Looking at the JSON-LD schema, I can see we have a Person type with various properties, and a nested PostalAddress type for the address.
>
> Let me create the schema structure with the appropriate types and elements:

`🔧 Tool called: core_models_bulk_create`

> **Neo**
>
> Perfect! I've successfully created the Person schema from your attached file in CoreModels. Here's what I created:
>
> Schema Structure Created
>
> Types
>
> * **Person** - The main type representing a person
> * **PostalAddress** - Type for address information
>
> Person Properties (Elements)
>
> * **name** - Full name
> * **givenName** - First name
> * **familyName** - Last name
> * **alternateName** - Alternative name (like "J. Doe")
> * **birthDate** - Date of birth
> * **gender** - Gender
> * **email** - Email address
> * **telephone** - Phone number
> * **url** - Personal website URL
> * **image** - Profile image URL
> * **sameAs** - Links to other profiles (social media, etc.)
> * **address** - Address information (links to PostalAddress type)
>
> PostalAddress Properties (Elements)
>
> * **addressLocality** - City (like "New York")
> * **addressRegion** - State/Region (like "NY")
> * **addressCountry** - Country (like "US")
>
> Relationships Created
>
> * All Person properties are linked to the Person type using "Domain Includes" relations
> * All PostalAddress properties are linked to the PostalAddress type using "Domain Includes" relations
> * The address property has a "Range Includes" relation to the PostalAddress type, indicating it can contain PostalAddress objects
>
> The schema structure now matches your JSON-LD Person schema and is ready to use in CoreModels! You can extend it further by adding more properties, creating exemplars with sample data, or adding additional constraints using mixins.

Here is the result in CoreModels

<figure><img src="/files/FEmHBRV5A0PfCGCW4mDy" alt=""><figcaption></figcaption></figure>


---

# 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:

```
GET https://learn.coremodels.io/user-guides/neo-ai-agent.md?ask=<question>
```

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.