Share your location
Use GPS or search for your city above. Coordinates stay in this browser tab only.
Your weather & hazard view
See live source posture, short-term risk checks, medium-term hazard watches, and long-term climate/disaster signal hypotheses.
New here? Start in 3 steps
Like Apple Weather and Weather.gov, we lead with your area first — then show proof behind every read.
Use GPS or search for your city above. Coordinates stay in this browser tab only.
See risk level, time window, and active triggers in the live hazard card below.
Use a quick question for 24-hour, storm, or long-range risk — every answer links to proof.
Not emergency advice. Follow NWS, USGS, and local authorities for warnings.
Your local snapshot
Risk level, time window, and active triggers from official feeds. Education only — follow NWS and local authorities for warnings.
Intensity & window
Waiting for first card refresh.
Time window: —
Location: —
Feed honesty: —
Updated from NOAA & public sources
Popular questions
Pick a time horizon below — each question uses your location when it is on.
Rain, wind, and local risk for the next 24 hours — from NOAA and public feeds.
Where heavy rain and flood risk may build over the next two weeks.
Regions where weather, water, and fire signals are trending worse over months.
Behind the snapshot
No live proof items right now — that's normal. Your hazard card above uses the same official feeds.
Operator view — full sector cockpit with routes and audit objects.
This window shows what KELLY is doing in Weather Lab: what it is reading, what it thinks might matter, what proof exists, and what is still waiting.
Read the answer in this lab first. Open the proof shelf or JSON packet for the evidence behind it. Check the route status and last-checked timestamp before trusting freshness. Look for the mind-changer: the fact that would make KELLY revise the answer. If evidence is waiting, treat the output as a question or watch item, not a settled answer.
Live evidence appears only when KELLY exposes proof-linked sector output. Empty states are intentional waiting states, not filler.
New approved evidence, a falsifier, settlement, replay drift, calibration movement, or memory-lineage revision.
This lab communicates with KELLY as an inspection window. It cannot write ground truth, memory, GraphState, provider state, or reality receipts.
Processing flow
Sources
Proof standard
Outputs
Storage posture
Use canonical KELLY Neon/Postgres for hazard_observations, region_context, forecast_deltas, source_freshness, closure_windows, settlement, and calibration state.
Object storage
Use R2/object storage for immutable forecast packets, alert snapshots, map/source bundles, and replay receipts.
Volume
Optional local volume only for rebuildable map tile, geocoder, and model cache. It must never become canonical hazard memory.
Technical objects
Proof receipts
Authority