requirements

Instead of asking an LLM “Did this work?” you define verification steps that produce a series of pass/fail artifacts. The agent can’t negotiate with a failing test. It either meets the specification or it doesn’t.

You cannot write a spec that survives that environment unless you deeply understand the architecture, the integration boundaries, the edge cases, the failure modes, and the invariants that must never break. The spec is not a prompt anymore. The spec is the product thinking made explicit.

If you cannot articulate what success looks like in a way that can be evaluated, no amount of autonomous execution will produce it. Agents cannot clarify requirements they are never given. They will fill the gaps with assumptions, and those assumptions compound.

long-horizon agents assume requirements all exist upfront. They are fundamentally against human in the loop. And they don't have true judgment for what humans like. That—is why I don't like them.