Ideas / Shapes in knowledge

Lab

Knowledge an agent can cite

Can every fact an agent gives be traced to the passage it came from?

Documents read into a graph typed by an ontology, every fact traced to its passage, and an agent that cites them. Live on S&P 500 earnings, with the architecture open source as Knowledge Store.

Earnings Lab

Labs

  • Earnings LabPublic · Live data

    S&P 500 earnings in an ontology-typed knowledge graph, with the passage behind every fact and an agent that cites it.

Research

  1. How the agents are tested

    The Earnings Lab has two agents, one that reads earnings releases into a graph and one that answers questions over it. This covers how each is checked, what happens to a failure, and what is not tested yet.

  2. How the Earnings Lab is built

    The Earnings Lab turns US quarterly earnings releases into an ontology-typed graph, answers questions over it as the signed-in user, and scores itself against the figures companies file in XBRL. This covers its parts on AWS and what it costs to keep and to run.

  3. Ontology-guided GraphRAG

    Question answering over a knowledge graph whose only schema is one curated OWL ontology, which shapes what gets extracted, how the graph is typed and how an agent queries it.