World Intelligence

Ask the analyst what the press is saying about X and get a structured, bias-contextualized read, not a misleading average. The Layer-B engine (src/features/world-data), the deterministic world-schedule dispatcher, scripts/oshal-world.js, the world-analyst registry entry, and the default tile stay framework-resident; this package is the /api/world surface (fail-closed header-authenticated writes, open reads), the world-analyst manifest, the seven world_* tools, and the refresh/pulse schedules.

• World Sentiment (bias-aware). Bias-aware sentiment for a world subject. Returns the structure a naive average destroys: the POLITICAL axis (byLean left/center/right), the ECONOMIC axis (byEcon…
• Ingest World News. Fetch, classify (Claude via the swarm's creds), bias-rate, and ingest current news for a subject across the registered feeds into the shared graph + series
• World Entity Graph. Graph neighbourhood of a world entity — the people, orgs, tickers, places, and outlets co-mentioned with it
• World Metric Trend. Historical average of a world metric (sentiment, *_mention) for an entity over N days — the time-series the reasoner joins against
• World Pull-Rate. Pull-rate accounting for a subject — per source: fetched vs unique vs new, and freshness. Input: {entity, days?}
• World Subjects. List the world subjects already tracked (ingested) with their item counts — so you know what coverage exists before reading or ingesting
• Contribute to World Knowledge. WORLD KNOWLEDGE — the universal inbound. Push structured knowledge (entities + edges + facts, with provenance) into the SHARED world graph that the whole swarm reads

1. 01

   You open it, or the assistant does

   Opening ?app=world loads its 1 screen into the shared cockpit, starting on world-dashboard. The ribbon, the ticket list and the assistant are already there — the app contributes views, not a second application to log into.

2. 02

   Or you just ask

   The assistant classifies what you asked for and hands it to the bot that owns that domain. You do not pick the app, and you do not learn a command — routing is by declared capability, not by keyword matching a menu.

3. 03

   A named bot picks it up

   world-analyst is accountable for the work. 5 declared capabilities say what it is trusted to do; the tokens and dollars it spends are recorded against that identity, so the cost has a line item rather than disappearing into a monthly bill.

4. 04

   Longer work becomes a ticket

   Scheduled and swarm-initiated work enters the queue as a world ticket. It is durable, it has an owner, you can watch it move through its phases, and if it fails it fails somewhere you can open and read.

5. 05

   The result lands where you can check it

   Back on the app's own screens, as state you own — not as a chat message you have to scroll back to find.

• Routing is by declared capability, not by keyword. world-analyst advertises what it is accountable for, and the assistant matches against that.
• Asks that land here: anything about world query, anything about sentiment analysis, anything about news ingestion, anything about entity extraction, anything about bias analysis.
• The specialist does the work, not the assistant. Cost, permissions and audit stay attached to the bot above — delegation does not launder accountability.
• It will tell you when it cannot. If a request needs your screen — an approval, a payment, a login — it says which app to open rather than guessing.

All 6 knowledge apps →