All books

Graph Systems

Knowledge-Driven Agent Architectures

Use ontologies and graph evidence to constrain plans without confusing knowledge with authority.

10 chapters · 6-8 hours reading · 4-5 hours labs · 10-15 hours project

Chapters

  1. 1The knowledge agent as a bounded transition systemMental model
  2. 2Typed plans, preconditions, and action schemasFormal planning
  3. 3Ontology-constrained planning and validationSemantic control
  4. 4Graph evidence acquisition and claim ledgersKnowledge retrieval
  5. 5Temporal state, memory, and event historyDurable cognition
  6. 6Tool orchestration, budgets, and durable executionRuntime engineering
  7. 7Staged writes, authorization, and compensationSafe action
  8. 8Knowledge-agent threat model and fail-closed designSecurity engineering
  9. 9Trajectory evaluation, counterfactual replay, and red teamsAgent evaluation
  10. 10Production governance, observability, and capstoneOperational mastery