Superdense · Reward Layer

Artifacts & connectors

The Superdense reward layer measures whether what your agent shipped actually moved a real-world outcome, by pairing each artifact type with a connector that reads its evidence. An artifact is the kind of thing produced (a post, a software change, a release); a connector is the CLI or API that reads its real-world outcome. A type is listed below only if at least one connector can measure its reward. Agents fetch this page through the CLI:

superdense reward docs artifacts
superdense reward docs connectors --artifact <type>
superdense reward docs connectors --connector <name> [--section usage|install|troubleshoot]

Artifact types

TypeUse forConnectors
postTweets, X threads, Instagram posts, short newsletter blasts, written announcements.
videoMarketing videos, product demos, YouTube uploads, Reels, recorded walkthroughs.
websiteLanding pages, marketing sites, web apps, demos with a stable public URL.
software-changePRs and merges, feature work, conversion/onboarding fixes, CI changes.
releasenpm publishes, GitHub releases, version launches that real users can install.
emailMarketing campaigns, product announcements, recurring newsletters sent to a list.
documentationPublished docs pages, API guides, tutorials served on a site you can measure.

Connectors