Ho System, Actually Build the software. Develop the judgment.

interaction test

definition
depth 3/3 − deeper + surface

A human at a real terminal checking that something works and feels right, not just that the code runs.

A validation modality (b): a human, hands on a real terminal, checking function plus feel—the UI/UX a smoke test structurally can't reach (the delta between clean chosen input and a real human's messy TTY). Produces commits, no document—a practice, not an artifact type.

The Validation Layer. The verification stack answers one question: did we build it right?—does the code match the spec. Every layer in Section 2 serves that question. It is only half of quality.

The other half is validation: did we build the right thing, and is it good? A system can pass every test, clear every linter, and survive cross-agent and human architectural review—and still be the wrong thing, or a right thing that is confusing, unpleasant, or useless in real hands. Verification cannot catch this, because verification measures conformance to a spec, and the spec itself is what validation interrogates.

This is Section 1's thesis extended. The research there—that humans overestimate AI-assisted work—was about correctness. It holds at least as strongly for goodness. An agent reporting "the feature works" is reporting that it ran; it is not reporting that the feature is good, because good is not a property the agent is positioned to judge. Validation is the antidote to overconfidence about goodness, exactly as verification is the antidote to overconfidence about correctness.