Symphony of data and knowledge
Knowledge Orchestrator + IBM digital rendering of white circle with a flower design
The impact of corporate knowledge loss

Following the sudden death of a key person from his team, Dr. Errol Brandt was driven to find a better way to preserve corporate knowledge and mitigate the risk of catastrophic knowledge loss.

Catastrophic knowledge loss occurs when organizations suddenly discover that critical business processes are disrupted by incomplete organizational understanding.  It can take many forms but it’s most commonly seen when unpacking complex spreadsheets that run critical business processes.

The inability to access deep tacit technical knowledge, made pricing and capital investment decisions much harder, which impacted business performance.

As a part of the knowledge recovery plan, Dr. Brandt started building a prototype as a passion project on IBM Cloud®. By late 2022, the product was ready for testing, and with the help of two co-founders Dr. Brandt formed Knowledge Orchestrator Pty Ltd to begin commercializing the solution.

Today Knowledge Orchestrator considers itself “client zero” and uses the solution to document every aspect of its business and empower its team to be productive from anywhere.

Employee productivity

Knowledge updates per employee per month
We now have clear evidence AI-powered applications can significantly augment employee productivity; the numbers speak for themselves. Dr. Errol Brandt Chief Innovation Officer Knowledge Orchestrator, IBM Business Partner
An enterprise knowledge management platform—powered by AI

IBM technology enabled Knowledge Orchestrator to realize its vision of creating an enterprise knowledge management platform powered by AI.

Knowledge Orchestrator developed its solution using a unique approach that it calls PEG, for pre-enhanced generation. Unlike retrieval-augmented generation (RAG), which helps to validate content generated by large language models (LLMs), PEG is focused on building high volumes of automated ground truth. This is done through a unique content generation algorithm, which was built and developed on IBM Cloud using the IBM® AI studio.

The platform turns raw, unstructured data, such as sales data, into structured natural language, which is then available as ground truth. Knowledge is segmented into specific domains, which allows the algorithms to work more effectively. This approach reduces the cost of inferencing and the risk of hallucination. Up until now, these have been major barriers in using generative AI to perform management analytics.

Improving employee productivity and engagement

Knowledge Orchestrator has been using it own solution for 12 months and it has far exceeded expectations.

Today, with a team of five full time equivalents (FTEs) plus KIRA, an AI assistant, the company’s enterprise knowledge base contains more than 2,000 articles (or 500,000 words). While the size of the digital knowledge base is interesting in its own right, what’s more important is the underlying employee engagement. The data shows that each employee each day, on average, reads 9.3 articles and writes 0.9. This incredibly high level of engagement is only possible because every aspect of their business is recorded in the enterprise knowledge platform.

IBM’s solution, bought with help from Meier Business Systems (MBS), has solved the business problem in various ways.

First, by providing access to enterprise-grade cloud architecture on IBM Cloud, the solution was deployed inside a Kubernetes cluster. This helped to promote future scalability, availability and efficient resource management.

Second, the solution makes use of the IBM Carbon Design System, which provides a cohesive set of design guidelines and components to support a seamless, accessible user experience.

Finally, and importantly, the advanced technology behind Knowledge Orchestrator’s unique content generation algorithms were designed to run entirely within IBM This allows Knowledge Orchestrator to take advantage of IBM’s extensive catalog of cloud-based services and APIs, including natural language processing, speech to text as well foundation models such as Google Flan, Facebook Llama and IBM Granite for task-specific language processing.

The solution is in final stage testing with a handful of foundation customers, who are using it to augment the capabilities of their sales teams. From there the functionality will extend into other areas of the business, including sales forecasting, production analytics and profitability simulation.

Knowledge Orchestrator is now looking to work with IBM to scale the solution and bring the power of LLMs to more enterprises.

South Waikato District Council logo
About Knowledge Orchestrator

Established in 2022, Knowledge Orchestrator (link resides outside of is a knowledge as a service (KaaS) solutions provider that helps users to engage with their corporate knowledge base. The company’s offering is designed to facilitate the sharing, learning and discovery of knowledge within an organization

Company cofounder Dr. Errol Brandt is a fellow of the Australian Society of CPAs and a Graduate of the Australian Institute of Company Directors. He holds a Doctorate in Business Administration, for which he researched corporate sustainability in the Australian Manufacturing Sector. He speaks about the opportunity for organizations to augment productivity with advanced technologies, and has been recognized as an IBM Champion in Data and AI (2023 and 2024). is helping companies custom-build AI solutions to suit their specific needs.
Explore View more case studies

© Copyright IBM Corporation 2024. IBM Corporation, New Orchard Road, Armonk, NY 10504

Produced in United States of America, April 2024.

IBM, the IBM logo,, IBM Cloud, and are trademarks or registered trademarks of International Business Machines Corporation, in the United States and/or other countries. Other product and service names might be trademarks of IBM or other companies. A current list of IBM trademarks is available on A current list of IBM trademarks is available on

This document is current as of the initial date of publication and may be changed by IBM at any time. Not all offerings are available in every country in which IBM operates.

All client examples cited or described are presented as illustrations of the manner in which some clients have used IBM products and the results they may have achieved. Actual environmental costs and performance characteristics will vary depending on individual client configurations and conditions. Generally expected results cannot be provided as each client’s results will depend entirely on the client’s systems and services ordered. THE INFORMATION IN THIS DOCUMENT IS PROVIDED “AS IS” WITHOUT ANY WARRANTY, EXPRESS OR IMPLIED, INCLUDING WITHOUT ANY WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND ANY WARRANTY OR CONDITION OF NON-INFRINGEMENT. IBM products are warranted according to the terms and conditions of the agreements under which they are provided.

The client is responsible for ensuring compliance with laws and regulations applicable to it. IBM does not provide legal advice or represent or warrant that its services or products will ensure that the client is in compliance with any law or regulation.