An idea, a research report — or a screen recording. shipd turns a recording into a cited brief, grounded frame by frame: every claim carries a timestamp, a speaker, and the frame that was on screen when it was said.
Agents investigate your codebase first, climb the question ladder for what's left, and compile intent into three reviewable artifacts: a plan with its decisions, testable requirement deltas per capability, and a mechanical task list.
A context-sufficiency gate checks the plan against the real codebase before a line of code is written. Insufficient context parks the plan as rejected for human enrichment — the system never builds on a guess.
The orchestrator designs on the strongest model; execution agents one tier down claim tasks atomically. Then an independent validator tries to refute every scenario in the spec against the real, running code. Refuted goes back; only confirmed moves on.
CI and a semantic review that must be explicitly dispositioned gate the merge. On ship, the deltas merge into a versioned capability library and the change archives — the system always knows exactly what it can do.
Before shipd asks you anything, it climbs a ladder: the codebase first, then the workspace wiki and personal memory store, then an "ask-first" oracle holding your standing positions. Only a question none of them can answer reaches a human — and once you answer, the answer is recorded so it's never asked twice.