Platform Overview

MediaWiki Foundation

Our platform is based on MediaWiki, the software that drives Wikipedia. We chose this platform for two reasons:

1. Open-Source Nature: It’s open-source, meaning we don’t spend a lot of time or money reinventing the wheel.
2. Battle-Tested Technology: The underlying technology has been around for more than 20 years, making it one of the most battle-tested pieces of software on the planet.

We have heavily modified the skin and layout of the wiki to suit our needs and enhanced it to handle modern cybersecurity threats. Despite these modifications, the core functionality remains reliable and secure.

User Interface

Knowledge Orchestrator Platform

The Knowledge Orchestrator platform is the user-facing component of our system. However, it represents just the tip of the iceberg. Beneath this surface, there are several layers of advanced proprietary technology, some of which are covered by patents. The platform is built entirely within the IBM Cloud and leverages IBM’s leading Watson Analytics platform at its core.

Backend Components

Content Orchestrator

Beneath the user interface lies the Content Orchestrator, a set of tools that manage the creation of content. Content here can refer to a wide range of formats, including:

• Wiki articles
• Spreadsheets
• Presentations
• Audio files
• Video files

Two additional modules feed into the Content Orchestrator:

1. Analytics Orchestrator
2. Insights Orchestrator

Data Processing

Analytics Orchestrator

The Analytics Orchestrator is a set of tools that load and transform raw data for the Content Orchestrator to process. This raw data can come from various sources, such as:

• Spreadsheets
• Internal SQL databases
• ERPs

This module cleans and slices the data, making it available for content generation.

Insights Orchestrator

Working alongside the Analytics Orchestrator, the Insights Orchestrator uses Artificial Intelligence technologies, such as neural networks, to derive new insights from data.

Example Workflow

Sales Analysis Use Case

1. Data Ingestion: Customer data is ingested from internal sources.
2. Data Processing: The Analytics Orchestrator cleans and segments the data.
3. Insight Generation: The Insights Orchestrator incorporates external information, such as weather and government statistics, to predict future sales.
4. Content Creation: The combined dataset is sent to the Content Orchestrator to generate articles in multiple languages (e.g., English, French, Japanese).
5. Platform Update: The generated content is updated into the Knowledge Orchestrator platform.

Benefits

Without human intervention, we can create—or orchestrate—corporate knowledge with unprecedented speed and precision. Our customers benefit from advanced technology platforms, such as IBM Watson, without the need to purchase expensive servers or hire costly resources.