# Overview

CKEditor AI turns your editor into an agent that reads, writes, and edits documents, and keeps your markup intact.

Ask it to rewrite a paragraph, check a whole contract against your style guide, translate a manual, or fetch live data during a chat. The same agent runs behind a chat panel, a one-click action, and a backend job with no editor open.

The agent is an HTTP service. It edits rich text HTML, one element or the whole document, and it knows the markup CKEditor 5 produces. The CKEditor AI plugin connects the editor to it, and your backend calls the same endpoints.

To run your first call against a real document in a few minutes, see [Quick start](quick-start.md).

<a id="what-you-get-over-a-general-purpose-ai-agent">

## What you get over a general-purpose AI agent

The difference from building on a general-purpose agent is in what you get back, and in how much you have to build and maintain yourself.

* **We maintain CKEditor 5 compatibility.** The agent knows the markup behind each editor feature, and we update it with every editor release. Doing this in-house means tracking every editor and model release yourself.
* **Humans stay in the loop.** The agent returns a proposed change per element, not a rewritten document. In the CKEditor AI plugin, each one arrives as a track-changes suggestion, and a person accepts or rejects it as they would a colleague’s edit.
* **Your markup stays intact.** A general-purpose agent returns new text, and there is no guarantee that tables, CSS classes, or unrelated sections survive. The agent changes only the necessary elements and leaves the rest alone.
* **Long documents are supported.** A long document does not fit in one model call. The agent reads the parts a request needs and can apply one instruction across the whole document.

To learn how the agent handles a request, see [How CKEditor AI works](how-it-works.md).

<a id="extend-our-agent">

## Extend our agent

You can extend the agent in several ways:

* **[Context library](extensions/context-library.md)** holds reusable prompts and files in your environment, such as your house style or a glossary. You reference them by ID instead of pasting them into every request.
* **[Model providers](extensions/model-providers.md)** are the models the agent runs on. On SaaS we operate them, and [Models](models.md) lists them. On-premises you configure at least one provider yourself, from the major cloud providers to any OpenAI-compatible service.
* **[MCP tools](extensions/mcp-tools.md)** connect the agent to your systems through MCP servers, so it can look up current data or perform actions while it works. MCP resources can also be added to a context as files.
* **[Hooks](extensions/hooks.md)** connect the agent to a service you already run. Your service can answer the request itself, refuse it, or add context before the agent replies.
* **[Skills](extensions/skills.md)** teach the agent the markup behind a CKEditor 5 feature, so it returns content the editor accepts.

Each extension pairs with some endpoints and not others. See [Compare extensions](extensions/overview.md#compare-extensions) before you plan an integration around one.

<a id="use-cases">

## Use cases

The table shows what each use case does and which extensions it uses.

| Use case                                                               | What it does                                                                                | Extensions                 |
| ---------------------------------------------------------------------- | ------------------------------------------------------------------------------------------- | -------------------------- |
| **[Check drafts against your style guide](apply-your-style-guide.md)** | Reviews a draft against your own style guide and suggests corrections                       | Context library            |
| **[Fetch data from your systems](fetch-data-from-your-systems.md)**    | Lets writers ask the chat for live data from your internal systems instead of pasting it in | MCP tools                  |
| **[Extend your agent’s capabilities](extend-your-agent.md)**           | Brings your company’s own agent into the editor chat alongside ours                         | Hooks, Context library     |
| **[Moderate content with your own rules](content-moderation.md)**      | Applies your own rules to what the chat may answer                                          | Hooks                      |
| **[Edit documents from your backend](verify-with-your-tools.md)**      | Edits documents automatically in a backend job, with your own checks applied                | MCP tools, Context library |

The two scenarios built on hooks need an on-premises deployment.

<a id="ways-to-use-it">

## Ways to use it

* **In CKEditor 5:** the CKEditor AI plugin adds [AI Chat](../../../../ckeditor5/latest/features/ai/ckeditor-ai-chat.md), [AI Quick Actions](../../../../ckeditor5/latest/features/ai/ckeditor-ai-actions.md), [AI Review](../../../../ckeditor5/latest/features/ai/ckeditor-ai-review.md), and [AI Translate](../../../../ckeditor5/latest/features/ai/ckeditor-ai-translate.md) to the editor. The [CKEditor 5 AI documentation](../../../../ckeditor5/latest/features/ai/ckeditor-ai-overview.md) covers what they do and how to configure them, and this guide covers the token endpoint, the deployment, and the extensions.
* **From your backend:** [Document Processing](document-processing.md) edits documents with no editor open. You send one or more documents with a prompt and get back the edited documents and a summary of what changed.

Both paths call the same HTTP endpoints, and [REST API](rest-api.md) lists them. CKEditor 5 can call Document Processing too, through a gateway, and [Using CKEditor AI programmatically](../../../../ckeditor5/latest/features/ai/ckeditor-ai-programmatic.md) covers it.

<a id="deployment">

## Deployment

* **[SaaS](saas.md)** is our cloud. You call our API and we operate the service.
* **[On-Premises](on-premises.md)** runs the same service as Docker containers on your own infrastructure.

Most of this guide applies to both. A page that applies to one deployment only says so at the top, and [Features that need an on-premises deployment](on-premises.md#features-that-need-an-on-premises-deployment) lists them.

> **Note**
>
> [Security & compliance](security-and-compliance.md) covers what data leaves your infrastructure, where it is processed and stored, and for how long. Use it for security reviews.

<a id="next-steps">

## Next steps

* **[Authentication](authentication.md)** covers the token your requests carry, from the one you get for testing to the endpoint you run in production.
* **[Permissions](permissions.md)** define what each user’s token may do.
* **[Usage and billing](usage-and-billing.md)** reports what your environment and each of your users consumed.
* **[REST API](rest-api.md)** links the API reference and lists versioning, pagination, limits, and error codes.

> **Note**
>
> To evaluate CKEditor AI, start a [14-day free trial](https://portal.ckeditor.com/checkout?plan=free) or [talk to sales](https://ckeditor.com/contact/) for a larger deployment.

---

Full index of the Cloud Services documentation: [llms.txt](../../../llms.txt)