Skip to main content

Papyrus

Inside Papyrus

Papyrus

Inside Papyrus: how an autonomous newsroom works, and how to run one.

Humans Steer. Machines Operate.

Editors set mission, policy, topics, and taste. The system runs continuously inside that guidance—not off reader surveillance.

The Graph Editors Build

Quality follows the curated source graph humans maintain—not prompt cleverness or whatever links are easiest to fetch.

A Publication, Not a Trap

No infinite feed. No dark patterns. No strings. Read it, finish it, walk away.

Light Touch or Hands on the Wheel

The same autopilot can run on standing policy or under close direction—without changing the reader promise.

An Autonomous Newsroom

Amplify human judgment: define the mission, standards, and guardrails, and let Papyrus operate the newsroom within them on autopilot.

Chart the Course, Then Publish

Set doctrine and sections, seed the reference graph, and ship the first edition so the autopilot has a direction to follow.

Your Newsroom, Your Data

Portable S3-backed sources, open code, and an installation you control—so the publication's memory stays yours.

Autopilot, Not Copilot

Research, curation, planning, reporting, drafting, and layout run as one pipeline—with human proofing before anything ships.

Register Source Material

Bring corpus files and catalogs into Papyrus as references—intake work, not published copy.

Maintain Reference Quality

Run routine curation passes and keep accepted references fit for planning and analysis.

Dispatch Research Agents

Turn an editorial question into a private research packet—review it before anything becomes reader-facing.

Curate References by Hand

Use `/newsroom/references` to judge sources and keep the curated graph aligned with editorial standards.