Each morning, after the council settles its convictions, the scan reads the day's news against every live thesis and reports back three things: what confirms it, what threatens it, and what merely surrounds it.
The conviction council is excellent at forming a view — it weighs the brokers, weighs the theses, and lands a net signal per theme. What it does not do on its own is check that view against what happened in the world today.
A conviction is only as good as its exposure to disconfirming evidence. The Signal News Scan closes that gap: it turns each standing thesis into a daily question — did reality move toward this thesis or away from it? — and answers it with cited, current developments, right inside the same client report the conviction already ships in.
The council decides what we believe. The scan tests, every day, whether the news still agrees.
Most news pipelines summarize. This one adjudicates. Every candidate development is paired with a specific theme's thesis and its stated invalidation trigger, and the classifier returns one of three stances — nothing else.
The development moves reality toward the thesis. Evidence the council's read is holding.
The development cuts against the thesis, or trips its invalidation trigger. The signal to look at first.
Relevant and worth seeing, but not decisive either way. Deliberately un-opinionated — it does not inflate the case.
The classifier may only cite items from the day's fetched pool — never its own memory. A thesis it can't support with a real, dated, linked article gets CONTEXT or nothing. No invented evidence, ever.
Thesis. Panel is net bullish on structural AI-hardware demand — cleaner semiconductor setup, power-architecture change — against Zerohedge's conditional bear that AI capex is cyclical and vulnerable if the largest spenders change behavior.
Invalidation trigger. A meaningful pullback or behavioral shift in capex plans by the largest AI spenders.
The scan is not a separate schedule to babysit. It is a sub-workflow the daily report calls inline, immediately after the conviction council has produced its signals — so it always classifies against that morning's convictions, never stale ones. Its output is handed back as a rendered HTML block and injected straight into the report body, after the conviction section.
Every stage tolerates emptiness. A dead feed, an empty search, a malformed model reply — none of it can break the daily report. Worst case the section reads "No material developments," and the rest of the report ships untouched.
The reader never sees a pipeline. They see one new section in the daily report, grouped by theme, with the most consequential stance first — invalidations, then confirmations, then context. Each line is a plain-language read plus a cited, clickable source. Quiet themes say so, rather than padding.
Below: the actual rendered output from the first live run (exec 39870), verbatim.
No material developments since analysis.
The design question was never "how much news can we pull" — it was how much signal per unit of noise, without contaminating the corpus that drives conviction. Three constraints shaped every source decision.
A source only counts if it produces a dated, linkable item. That rules out anything the model can't attribute — no "general sentiment," no un-sourced claims.
News lives in its own store. The broker research embeddings that feed the council are held completely separate — a hard invariant, so daily noise can never leak into conviction.
A single daily run: one scoped search, one classifier pass, one write. Breadth is added by editing an allowlist, not by widening an expensive net.
Curated RSS gives reliable, reputable baseline coverage at near-zero cost. Thesis-scoped web search reaches the specific, the breaking, and the long-tail a fixed feed list misses. Running both, then merging into one deduped pool, is what produced the SK Hynix and Hormuz reads above — neither was on an RSS front page.
The starter allowlist is intentionally small and reputable — chosen to prove the loop, not to be exhaustive. Adding a wire is a one-line change; the table below is the roadmap, not a limit.
| Source | Kind | Why | Status |
|---|---|---|---|
| Reuters | Wire · RSS | Broad, fast, reputable market & macro baseline | LIVE |
| AP | Wire · RSS | Geopolitical & breaking, low-bias baseline | LIVE |
| CNBC | Markets · RSS | Equity & single-name market coverage | LIVE |
| FT | Markets · RSS | Macro, policy, and cross-border finance depth | LIVE |
| EIA | Energy · RSS | Primary-source energy data for energy/oil theses | LIVE |
| Web search | Open · scoped | Thesis-targeted long-tail & breaking, per theme | LIVE |
| Bloomberg / WSJ | Markets · RSS | Deepen equity & macro; some paywall friction | CANDIDATE |
| Sector trade press | Vertical · RSS | Semis, defense, mining, grid — match named themes | CANDIDATE |
| Regulatory / filings | Primary · feed | SEC, central banks, statutory registries — hard evidence | CANDIDATE |
| Earnings / transcripts | Primary · API | Capex & guidance — direct on invalidation triggers | CANDIDATE |
| Curated X / social | Social · API | Earliest signal; high noise — needs strict filtering | CANDIDATE |
Every candidate is judged on the same three constraints from Section 05. A wire that emits clean, dated, linkable items and stays out of the broker corpus is a one-line allowlist edit. Anything noisier (social, transcripts) earns a filtering layer before it's trusted.
Today the scan is a daily read. Its real value is that it makes conviction a closed loop — beliefs that are continuously tested against reality and can be scored, tracked, and acted on over time. The stances are already persisted per theme per day; that history is the raw material for everything below.
Brokers & theses land a net signal per theme.
Each thesis met with today's cited developments.
VALIDATES / INVALIDATES stored per theme, per day.
Reality-support informs the next read.
Conviction stops being a snapshot the council prints each morning and becomes a position that has to keep earning its place against the day's evidence. The scan is how it's held accountable.