Continuous monitoring — finding and reviewing new work

Verification status — 6 October 2026

The page and source audit records selected eligibility and scheduling checks. The scheduler control audit adds local failure tests for activation, cost checks, run outcomes and admin controls. These checks do not prove missed production runs, complete scheduler coverage or readiness to activate monitoring. The capability and population descriptions below are the August snapshot. The ongoing-campaign requirement later on this page remains approved; activation requires its separate existing checks.

Monitoring should revisit sources, find new material and surface meaningful changes for review. The following inventory was recorded on 17 August 2026. Its statuses and counts are historical observations.

Earlier implementation inventory — 17 August 2026

Capability	Status	The honest detail
Newsroom ingestion	built	a production-grade service reads newsroom feeds and sitemaps; deliberately, it only collects — nothing it ingests is auto-analyzed
The re-scan scheduler	built, ships off	a background loop re-scans registered sources on a cadence, with admin controls and cost awareness. It defaults to off, and the smarter tier-aware cadence is deferred
Observations	populated	about 37,500 raw observations about content are stored, written by several stages
Risk signals	populated, per-piece only	about 4,600 risk signals exist — written during per-piece analysis, not by any standalone watching pass
Relationship events	populated, per-piece only	about 1,300 events recording owner-customer-partner edges, also written during analysis
A signals/alerts surface	empty	the dedicated signals table has zero rows — built, never wired
The daily recognition pass	missing	the ruled daily look at what changed — new campaign clusters, notable news — does not exist

What a build would decide first

• What "worth surfacing" means. The raw material is already flowing (observations, risk signals, relationship events); what is missing is the pass that reads it and decides what a person should see today.
• The news trigger. A newsroom press release or a trade article is often the first sign of a campaign — the recognizer and the monitor meet exactly here.
• Cost discipline. The scheduler ships off for a reason; turning monitoring on is a cost-cadence decision per source tier, not a switch.

Ongoing campaigns — required behavior

A campaign can continue without a planned ending. Monitoring must keep reviewing new work and its possible membership, with evidence available for correction. The campaign’s duration and purpose remain separate from the schedule used to check its sources. A missing end date alone does not prove that the campaign is ongoing.

This requirement was confirmed on 4 October 2026. It does not refresh the August implementation inventory above or authorize a schedule. Current collectors, prompts, membership writes, review controls, costs and delivery outcomes still need end-to-end verification before activation. The decision and reasoning preserve the approval.

Where to look next

• The campaign pipeline — what the daily pass would feed.
• The conformance report — where the model and the live data disagree.