Case files · updated from the live journal

What we called, when we called it, and what happened next

Every case below is reconstructed from Vigilo's append-only prediction journal — timestamped before the outcome, scored after it. No retrofitting: the same journal also records every miss, and the totals are public.

353confirmed calls
73.7%precision [CI 69.6–77.4]
13.5 daverage lead time
0.19Brier score (calibration)
+17%vs naive @ 7 days, blind test
31days lead

Sudan — escalation flagged from a quiet news cycle

Tier: Covert-elevated

Sudan produces little international coverage between flare-ups, which is exactly when conventional monitoring goes blind. Vigilo's covert-elevated tier exists for this case: it weighs the country's structural base-rate against unusually quiet signals.

Called 2026-07-13 → escalation confirmed 31 days later. Journal entry timestamped before the event.

Verification: public scorecard, confirmed_calls feed.

30+days lead ×3

Myanmar — three consecutive calls, all confirmed

Tier: Watch

A single lucky call proves nothing. Myanmar shows the system repeating: three separate watch-tier calls issued 2026-06-05, 07-07 and 07-08 — each confirmed with a 30–31 day lead. Repeatability on the same country is what separates a model from noise.

3 of 3 calls confirmed · leads 30, 30, 31 days · same tier, same method.

Verification: public scorecard — Myanmar rows.

52days notice

Vietnam — navigating the typhoon season, not cancelling it

Layer: seasonal climatology + live GDACS tracks

Most advisories say "typhoon season — reconsider travel" for two whole months. Vigilo's seasonal layer marks the storm corridor for central Vietnam and issues a usable answer instead: the safe window. Travellers got "aim for Oct 22–31, south is calmer than center" while agencies were still issuing blanket warnings — and each incoming typhoon is then tracked 2–5 days out on official forecast tracks.

Season window published from climatology weeks ahead; per-storm alerts follow GDACS forecast tracks, not landfall news.

Layers: risk_calendar (seasons) + GDACS multi-country tracks.

3+months ahead

Russia — an election window known long before the news cycle

Tier: Scheduled (known future)

Not everything needs prediction — some risk is simply scheduled. The Duma election window (Sep 19–22, 2026) sat in Vigilo's public risk calendar months in advance, with practical guidance attached: complete in-country business and flights before Sep 15. The known future is the cheapest early warning there is — if your system bothers to read it.

Election windows for 60+ countries, parsed continuously; each feeds the scheduled tier ≤45 days out.

Layer: risk_calendar.json — elections + curated geopolitical dates.

What we don't claim

Recall against external ground truth is 58% (USGS M6+ benchmark) — we catch most, not all. Precision 73.7% means roughly 1 call in 4 doesn't confirm. The journal is append-only: misses stay on the record, and the model re-validates itself blind every 8 hours (public/model_validation.json).

We publish these numbers because nobody else in this market does — and because a client who knows our error rate can actually plan with us.

See it live on your countries

30 minutes: your locations, your routes, our layers — on screen.

Book a walkthrough Inspect the raw scorecard