Geopolitical Daily

How it works

From 87 sources to one five-minute briefing

Every issue is produced by the same automated run: collect, group into events, let a language model write the issue, then check its work in code. Here is each step, what is AI and what is not, and what stops a bad issue from going out.

87sources across 15 perspectives
1,164articles read for the Nov 22 issue
2AI calls per issue — everything else is plain code
$0.025average AI cost per issue (last 10)
6 minstart to published, latest run
code AI model call (the only paid steps) optional — the issue ships without it if it fails
  1. 87 sources · 15 perspectives

    85 RSS feeds + 2 scraped sites; 55 are non-Western and 15 are state-affiliated (always labeled).

  2. Collect and enrich

    All feeds are fetched in parallel. Short RSS summaries are replaced with the article's full text; articles readers could not read (non-Latin script) are skipped.

  3. Group articles into events

    Sentence embeddings and density clustering put every report of the same event in one group — so a Western and a non-Western account of one event sit side by side.

    Fallback: if the embedding model cannot load, plain title-similarity de-duplication keeps the run going.

  4. Pre-select what the model reads

    Events are ranked by how many outlets confirm them and how many different perspectives cover them; up to four articles per event are kept, from different perspectives.

  5. AI call 1 — write the issue

    One call picks and ranks the top stories, writes the quick hits and the big number. The model also sees the last issues so it can lead with fresh events.

    Readability gate: copy above a 9.5 school-grade reading level is sent back for a rewrite (at most twice) — kept only if it reads easier without turning choppy or losing a figure.

  6. Editorial rules, enforced in code

    Running storylines move to Developing; items that repeat recent issues are dropped; links are checked against the text they sit under; headlines are set in sentence case; off-topic items (crime, celebrity, sport) are removed.

  7. AI call 2 — how the world covers it

    For the big story the model gets the event's articles grouped by perspective and returns each group's framing plus one quote. The Blindspot is picked by code: an event reported by at least two outlets we track, none of them Western.

    Quote check: a quote must appear word for word in the source article, or it is dropped.

  8. Signals

    Prediction-market odds and news-volume trends for the big story, added only when a market matches the story's specific names.

This website

The issue page, a permanent page per story, archive and RSS.

Email

Sent to daily subscribers; delivery is verified after sending.

Issue JSON

Machine-readable copy with model, cost and decisions. Feeds the Sunday digest — no AI needed.

Numbers on the arrows are from the November 22, 2026 run. Latest issue written by deepseek/deepseek-v4.1-flash-1017. Live figures for every issue are on the dashboard.

Every morning (UTC)
The daily run above: publishes the issue here and emails subscribers. A second start the same day does nothing once the issue is out.
Sundays
The weekly digest is assembled from the week's issue files for subscribers who chose one email a week.
Mondays
Every feed is tested; dead or blocked feeds are reported.