Coming soon
What we're building
The autonomous layer on top of decodx's agent tools — from a goal to a finished, reviewed video with no one at the keyboard.
Give an agent a goal — "a 90-second onboarding video for the new dashboard" — and it plans the scenes, not just fills a template.
It gathers what it needs: records the flows, drafts narration, picks a voice, and assembles the spec.
It renders, watches its own output, and revises weak scenes — iterating until the video meets the brief.
It opens the result for review the way a teammate would, with every decision captured in the spec.