AI Assistant for Redactor — Build AI Writing Workflows

Account

Menu

Buy now →

Model-agnostic · Server-side prompts · Structured document context · Sync, jobs, or custom transport

Build AI-assisted writing workflows inside your product

Redactor provides the document editor and review UI. You connect your own backend, prompts, and model.

How it works

The model returns data. Redactor turns it into an editing workflow.

Your document

Redactor sends the selected blocks or the full document as structured context.

Your backend

Your endpoint chooses the prompt, model, limits, logging, and data policy.

Redactor UI

The response becomes a review, report, list of alternatives, or an applied document change.

Redactor does not require a specific AI provider and does not add per-token billing.

Integration

Connect one endpoint

The editor sends an action ID and document context. Your backend selects the full prompt, calls the model, and returns the response shape expected by the selected mode.

Minimal initialization

Redactor('#entry', {<br>plugins: ['assistant'],<br>ai: {<br>url: '/api/ai/text',<br>model: 'your-model'<br>});

Minimal request

"action": "shorter",<br>"mode": "review",<br>"context": {<br>"scope": "blocks",<br>"blocks": [<br>"uid": "block-3",<br>"type": "text",<br>"tag": "p",<br>"content": "..."<br>},<br>"lang": "en",<br>"model": "your-model"

Response modes

One integration, several editing surfaces

Mode<br>Backend returns<br>Redactor shows

review<br>Issues and suggested content<br>Review cards with accept/reject

apply<br>Directly applicable issues<br>Changes or inline annotations

report<br>Title, tab and HTML<br>A document report tab

report-review<br>Report and optional issues<br>Report with reviewable fixes

Actions

Build the actions your product needs

Define actions around your own content, users, and editorial rules. Each action can use selected blocks or the full document, send additional context to your backend, and present the result as a review, an applied change, or a report.

Built-in actions provide working examples, but the menu, prompts, models, response handling, and application logic can all be adapted to your project.

Backend control

The editor sends an action ID and structured document context to your backend. Your application decides how that request is processed and what is returned.

Keep prompt templates on the server

Choose the model or processing pipeline for each action

Add user, tenant, document, or application context

Apply your own authentication and authorization

Set rate limits and usage limits

Control logging and data retention

Validate model output

Format structured responses for reviews and reports

The Assistant is not tied to a particular model provider. Your backend can call OpenAI, Claude, a local model, or a custom service as long as it returns the expected response format.

Events and extension points

Events let the host application inspect and modify the Assistant workflow at each important stage.

Modify or cancel a request before it is sent

Add custom fields and HTTP headers

Observe successful requests and errors

React when suggestions are accepted or rejected

Inspect content before insertion

Handle image-generation responses

Observe asynchronous job progress

Connect Assistant activity to application analytics or audit logs

Hooks that can change content or requests run before the corresponding action. Lifecycle events provide the result after the action has completed.

Transport options

Choose how Assistant requests reach your application. All transports use the same action context and return the same review or report response formats.

Sync

Send an HTTP request and return the completed result in the same response.

Jobs

Create an asynchronous job and poll your application until the result is ready.

Custom

Provide a JavaScript request handler instead of using the built-in HTTP transports.

Implementation guides and examples

The Assistant uses a small request and response contract. These guides cover the backend, prompt templates, asynchronous processing, and report output.

Write action prompts

Define server-side prompt templates that receive structured document blocks and return JSON for reviews, changes, and reports.

Read the prompt guide →

Connect a backend

See request and response formats with backend examples for OpenAI, Claude, text actions, and image generation.

View backend examples →

Run asynchronous jobs

Implement the create-and-poll protocol for long documents, queued processing, and slower models.

Read the jobs guide →

Build report output

Use the included HTML framework to present summaries, writing checks, key points, and other structured results in report tabs.

View the report framework →

Explore the complete API

Review configuration options, action modes, response formats, transports, events, and extension points.

Open the Assistant reference →

Pricing

Assistant Suite

Add-on for Redactor Core · Core not included

$699

Includes the AI Assistant, review...