Building AI systems to incorporate business knowledge typically involves chunking documents, selecting an embedding model, setting up a vector database, tuning retrieval processes, and possibly creating a graph. This complex infrastructure can make company knowledge less accessible and harder to interpret.

The Thinnernet project aims to create a parallel internet by integrating knowledge bases with ticket management systems to enhance proof of work. The initiative began in 2020 and is influenced by a humorous alter-ego inspired by Steve Jobs.

Quality control in knowledge work is critical, as errors such as outdated information, spelling mistakes, and mislabeled graphs can undermine the credibility of reports. Disregarding flawed reports can prevent decision-making based on inaccurate data.

Enterprise knowledge systems have struggled for sixty years due to issues related to familiarity. A senior executive at a global enterprise indicated that this familiarity was a key reason for not adopting a new AI product.

The Encyclopædia Britannica, 11th Edition (1910–1911) is fully searchable, cross-referenced, and annotated. It provides comprehensive articles across various topics.

llm-wiki provides a framework for creating personal knowledge bases using large language models (LLMs). It facilitates collaboration between users and LLM agents to develop specific functionalities beyond traditional retrieval-augmented generation (RAG) methods.

Captain offers an enterprise search solution that can deliver accurate knowledge retrieval in minutes. Users can power AI agents with their own data or utilize Captain's data through a simple API call.