AI Accelerator module

Generative AI Unbundled: Extension Version 1.3.0 Magnolia 6.2 compatible

The AI Accelerator module integrates ChatGPT, a powerful language model, to save time and energy for marketers and other editors throughout the content lifecycle, from planning and creation through to content optimization, classification, and rollouts of personalized content.

It lets you automatically generate:

Content, such as components, stories, and even entire pages.
Component variants for personalization.
SEO (Search Engine Optimization) and OG (Open Graph) metadata from page content.
Image descriptions based on image tags.

Hyper Prompt

The module includes Hyper Prompt. Hyper Prompt is an app that lets you create and reuse complex prompts that contain:

Your brand’s tone of voice.
Approved messaging content.
Keywords and other SEO considerations.

Create prompts for anything you need to generate brand-consistent content that aligns with your messaging strategy.

These features help speed up content creation, automate repetitive tasks, and improve content and design efficiency. All services are available in the Magnolia UI, comfortably embedded in the workflow that editors are familiar with.

Module architecture

Our AI automation module aims to provide seamless AI interactions within the user interface while ensuring secure and efficient backend processing.

UI Integration

The majority of the generative UI widgets are JS Field-based. This allows to extend the feature set based on our API layer.

Backend Integration

The module contains a proxy layer that acts as a buffer between the backend and the AI service. It helps in maintaining separation of concerns and potentially offers caching and other optimizations.

Additionally the layer ensures that calls to the AI service are correctly formulated and securely transmitted. Credentials to ensure authorized access are added on call from the frontend.

Credentials Management

The proxy layer ensures that AI service credentials are securely managed, appended to AI calls when necessary, and regularly rotated for security purposes. See the configuration section for reference.

AI Call Flow

Initiation from UI: Users trigger AI operations through the Magnolia JS Field.
Backend Processing: The backend receives the request, processes it, and forwards it to the AI service through the proxy.
Proxy Interaction: The proxy appends necessary credentials and routes the call to the AI service.
Response Handling: Once the AI service returns a result, the data flows back through the proxy and backend, eventually rendering the result on the Magnolia JS Field UI.