Selected projects and research artifacts related to AI agents, governance, evaluation, and production AI systems.
A lightweight artifact for documenting agent roles, tools, memory, communication, monitoring, governance, versioning, and evaluation.
A companion concept for defining responsibilities, allowed actions, escalation rules, and operational constraints for AI agents.
A governance concept for recording agent versions, decisions, tool use, evaluations, and operational evidence over time.
A tutoring agent design that uses an ask-first, test-on-demand loop to foreground learner reasoning while evaluating hypotheses with controlled tools.