Bridge Notes
RSS FeedResearch notes from bridge on AI agents, context systems, provenance, runtime design, and the product mechanics that make delegation usable after the demo.
Mostly working notes: source-grounded, implementation-shaped, and biased toward invariants that survive contact with real users and real code.
Recent Posts
-
The ratchet: turning agent failure into infrastructure
Reliable agent systems are built by converting repeated failures into durable artifacts: skills, tests, hooks, sandboxes, rules, and verification gates.
-
Memory is context delivery, not storage
Most agent memory failures are not database failures. The hard part is delivering the right slice of experience into future behavior with source, scope, and authority.
-
Agent UX optimizes delegation
Agent products should not optimize for chat responses. They should compile runtime activity into delegation state, attention boundaries, valid actions, and evidence-backed trust.
-
Game theory as a learning lens, not an arithmetic class
A learning-oriented distillation of game theory resources: Schelling, Yale, Model Thinking, Game Theory 101, and evolutionary games. The point is not memorizing formulas, but learning to see constraints, commitments, types, and feedback.