Agentic, long-horizon visual generation: a fuzzy story → a cross-model-audited image-based movie. Brings ARIS's research-wiki + multi-agent debate to multimodal generation (intelligence lives in the agent; the diffusion model just renders). Image-based today, video next.

Accessibility review agents for Claude Code, GitHub Copilot, and Claude Desktop. Eleven specialists that enforce WCAG 2.2 AA compliance so AI coding tools stop generating inaccessible code.