Pipelines — what we have, and what the model still needs

A pipeline is an automated path that gets something into the library and keeps it current. The domain model implies four of them, all fed by one shared routing-and-prompts layer. One is fully built. Two are partly built — more than we remembered. One exists only as fragments. The routing layer is built, with a dormant half. This page is the honest map; each pipeline has its own page with the detail. Every claim here was checked against the running code and the live database on 17 August 2026.

The map

Have versus need, in one table

Pipeline	Where it stands
The content pipeline	Built. Fifteen stages, verified against the code stage by stage
Brand onboarding	Partly built — more than expected. Entity enrichment works; a five-stage brand-guidelines pipeline exists and has run for twelve brands. Missing: a products-and-features harvest, and the "onboard this brand" routing step
The campaign pipeline	Fragments. A synthesis script exists but only runs by hand; the evidence machinery has run a handful of times across two campaigns; nothing detects a campaign on its own
Continuous monitoring	Partly built. Newsroom ingestion works; a re-scan scheduler exists but ships switched off. Missing: the daily recognition pass and any real alerting
Routing & prompts	Built, with a dormant half. Sixteen live routes pick a prompt by source; the smarter semantic layer exists but is switched off; prompts are hand-written today, and the ruled future is prompts generated from the registry

What each pipeline reads and writes (the tie to the data model)

Probed live on 17 August 2026 — this is where each pipeline's work actually lands:

Pipeline	Writes to	Watched through
The content pipeline	the piece's own fields + its classification links	the execution log — every model call with its stage and cost
Brand onboarding	the entity's facts · the brand-guideline sections	the same execution log
The campaign pipeline	campaigns · membership links · the two evidence surfaces	the intelligence run tables
Continuous monitoring	observations · risk signals · relationship events	the collection-run log; the alerts surface is built but empty
All of them	nothing runs on a schedule unless the single master switch is on — and it is off; every run so far was started by hand	one flag, one query

How to read the pipeline pages

Each page answers four questions in order: what this pipeline is FOR · what exists today (checked, with where it lives) · what is missing, named plainly · what a build would have to decide first. A missing pipeline is a to-do, never an argument against the model — the same rule the whole site runs on.