Exploring Bounded Semantic Decisions in WTK Agents and Teams
We are exploring where narrow model judgments could help, without giving them control over the workflow.
Full articleTrustworthy AI Agent Engineering Field Notes
Notes from the workbench.Short observations about the craft of accountable agent engineering, written before they harden into architecture claims.
Governing Improvement in Agents and Models
What should remain under independent control when the system proposes its own changes?
Full articleWho is responsible when an AI agent acts?
An enterprise approach to agent authority, team accountability, and governed improvement.
Full articleA Requirement Needs a Job
The right amount of structure is not more fields; it is a clear purpose for every constraint.
Full articleEvals Made the Agent Concrete
An agent becomes buildable when its purpose is translated into observable outcomes, bounded behavior, and evidence requirements.
Full articleGovern the Boundaries, Not the Reasoning
Flexible reasoning becomes dependable when purpose, authority, evidence, and acceptable outcomes remain governed.
Full article