We describe a virtual member of a knowledge management Community of Practice (CoP), called ATHENA, that knows an individual, his tasks, his organization, and the community. ATHENA employs an agentic chat capability that combines embeddings with knowledge-based faceted search to provide accurate responses to technical questions along with rationale and citations for efficient validation. ATHENA supports natural, in-the-flow capture of task-related insights to share within a CoP, along with proactive dissemination of information tied to an individual and his current needs. An evaluation involving 75 professionals from the Oil & Gas sector shows that ATHENA dramatically improved outcomes and productivity on a set of well-planning tasks compared to their use of a state-of-the-art RAG baseline. Interestingly, ATHENA also enabled eight non-experts to perform at expert levels.

This paper describes the genetic algorithm used to select news stories about artificial intelligence for AAAI’s weekly AIAlert, emailed to nearly 11,000 subscribers. Each week, about 1,500 news stories covering various aspects of artificial intelligence and machine learning are discovered by i2k Connect’s NewsFinder agent. Our challenge is to select just 10 stories from this collection that represent the important news about AI. Since stories and topics do not necessarily repeat in later weeks, we cannot use click tracking and supervised learning to predict which stories or topics are most preferred by readers. Instead, we must build a representative selection of stories a priori, using information about each story’s topics, content, publisher, date of publication, and other features. This paper describes a genetic algorithm that achieves this task. We demonstrate its effectiveness by comparing several engagement metrics from six months of “A/B testing” experiments that compare random story selection vs. a simple scoring algorithm vs. our new genetic algorithm.

The authors propose a model for an intelligent assistant to aid in building knowledge-based systems (KBSs) and discuss a preliminary implementation. The assistant participates in KBS construction, including acquisition of an initial model of a problem domain, acquisition of control and task-specific inference knowledge, testing and validation, and long-term maintenance of encoded knowledge. The authors present a hypothetical scenario in which the assistant and a KBS designer cooperate to create an initial domain model and then discuss five categories of knowledge the assistant requires to offer such help. They discuss two software technologies on which the assistant is based: an object-oriented programming language, and a user-interface framework.>