AI · Cockpit

One screen. Every signal.

Tune every AI signal, track your calibration across 12 forecast surfaces, and monitor your reading session — all in one place.

Opus
Sonnet
Haiku
session $0.00 · today $0.00 · month $0.00

Your signal controls

Forecast horizon
Source diversity · 5/10
Echo-chamber riskMax diversity
Doomscroll cap
Take aggressiveness

Prescience

demo48h horizon

Top forecasted catalysts

80%
prob
AI
15 articles · vel +250
30%
prob
Climate
6 articles · vel +30
31%
prob
Markets
3 articles · vel -25

Regime

MACRO
Confidence76%

Monetary and economic signals dominant. Fed-watch mode active. Read between the rate lines.

Takes

12AI takes today
Balancedaggressiveness

AI Takes activate in Phase 2 — cockpit substrate is live.

Fact-Check

47
Verified
3
Flagged

Fact-Check engine activates in Phase 2.

Doomscroll Shield

0:00
Cap: 30m
Stop now

Calibration · Brier-tracked surfaces

12 / 12 surfaces
Schema
pb-2026-05-03-v1
Total claims
34
Pending
34
Resolved
0
IDSurfaceHorizonClaimsStatusClimatology BS
S1Topic importance (24h)1d5pending0.100
S2Topic importance (72h)3d5pending0.120
S3Topic momentum (24h)1d5pending0.667
S4Topic decay rate (24h)1d5pending0.080
S5Topic decay rate (72h)3d5pending0.100
S6Breaking-topic catalyst (24h)1d1pending0.210
S7Cluster-forming catalyst (24h)1d1pending0.240
S8Topic-fading catalyst (72h)3d1pending0.210
S9Momentum-peak catalyst (24h)1d2pending0.240
S10Top-read "now" (4h)4h1pending0.210
S11Top-read "today" (14h)14h2pending0.250
S12Reader trajectory (7d)7d1pending0.667

Methodology: Brier 1950 — strictly proper scoring rule, lower is better. Climatology baselines refit quarterly once N≥30 per surface. Claims resolve at horizon-end via the resolution cron. Brier Skill Score (BSS) compares against climatology: 1.0 perfect, 0 no-skill, negative worse than baseline.

AI actions log

— No AI calls this session. Full audit log (timestamp · model · prompt-hash · tokens · cost · latency) activates in Phase 2. —