Product Overview: ErgoAI Platform

Note: ErgoAI is the new name for Ergo Suite

Introduction
Deep Reasoning via Advanced Logic
Features and Benefits
Architecture and Technical Approach
ErgoAI vs Flora-2 (open- source)

Introduction

ErgoAI excels at managing complex and changing information, which is important for automating many kinds of analysis and policies. It provides new methods for rapidly authoring structured logical information (i.e., encoded knowledge) starting from user-supplied English documents, and for powerfully reasoning with that knowledge to answer queries and present the conclusions in English. In other words, users assert and query knowledge in ErgoAI, or they can do so via custom applications built on top of ErgoAI. Automated decisions can then be made based on the results of the analysis. For example, compliance alerts can be generated automatically based on reasoning about policies and regulations that have been encoded into an Ergo knowledge base.

The meaning of an English sentence is captured deeply and precisely. Unlike previous systems, almost anything one can say in English can be encoded and operationalized, relatively easily, largely by the subject matter experts themselves. ErgoAI can then perform truly deep reasoning based on the encoded knowledge statements. This makes the automation of many aspects of analysis and decision making become much more affordable and practical.

Deep Reasoning via Advanced Logic

Under the covers, ErgoAI uses an advanced form of logic that is uniquely close to natural language, to represent the encoded knowledge and to generate conclusions. These conclusions are highly accurate and precise – much more so than question answering techniques based on statistical processing of natural language, such as Google web search. The user can see every step in the logical chain of reasoning that led to a conclusion, including the provenance and source information about the knowledge used in each step – an automatically generated audit trail. These full explanations can be provided in English or as logical statements. The user thus has full ability to inspect and evaluate the trustworthiness of all conclusions.

In many cases, knowledge statements conflict with each other. For example, one policy sentence may conflict with another policy sentence in the same document.  ErgoAI tolerates these conflicts and can harness them. Users can say which knowledge statement has higher priority based on criteria such as relative authority or recency. This makes it easy to add exceptions to previously accumulated knowledge.

Features and Benefits

  • Unprecedented flexibility in the kinds of complex information that can be stated as assertions, queries, and conclusions. In other words, knowledge statements can be highly expressive.
    • Almost anything one can say in English – concisely and directly
    • Just-in-time introduction of terminology
      • Start with existing ontologies if you have them. Add your own terminology as needed.
    • Statements about statements (meta knowledge)
    • Specify and inspect information at any desired granularity level
    • Unprecedented ease in updating knowledge:
  • Map between terminologies as needed, to tightly integrate information coming from multiple sources.
  • Conflict between statements is robustly handled (conflicts often arise during information integration due to errors and omitted context):
    • Conflicts are resolved based on priority (e.g., relative authority), or else tolerated as an impasse
  • Scalable and computationally well-behaved

Continue on to:
Architecture and Technical Approach