The Newspaper of One: Inside a Lights-Out Publishing System

Description and use

YUSKIMO’s automated publishing pipeline shows how separating evidence gathering from composition, verifying live pages, daily audits, and public failure logs enable a single operator to run a reliable, niche-focused newspaper with strong editorial accountability.

Problem

Automated publishing systems risk producing unverifiable content when operating in open domains, leading to credibility loss and brand damage.

Outcome

The system achieves reliable, verifiable publishing with minimal human intervention, enabling a one-person operation to cover niche topics with high editorial integrity.

Workflow

• 1. Evidence gathering agent collects structured data and sources.
• 2. Composition agent writes prose citing the gathered evidence.
• 3. Publish agent schedules and distributes content via APIs.
• 4. Fetch-back agent re-fetches the live URL to confirm rendering.
• 5. Daily audit loop checks all live pages, endpoints, and email deliverability.
• 6. Failure log records and publicly documents any publishing errors.
• 7. Human editor reviews salience, trust decisions, and accountability statements.

Evidence

The agent that gathers evidence is a different step from the agent that composes prose, and the composer is required to cite the evidence it was given.

Source

Every publish is followed by a fetch-back. Nothing is considered published until the system has re-fetched the live URL and confirmed what actually rendered.

Source

A scheduled audit loop with teeth. A daily heartbeat checks every live page, every endpoint, every e-mail deliverability record.

Source

Rate limits as an editorial calendar. Fixed daily cadence forces the machine to choose among its material.

Source

Failure log as first-class output. I documented it publicly rather than quietly patching, because a publishing system's credibility compounds the same way a newspaper's does.

Source