2026 product definition

Truth console · process is not world truth

Plug any model in as the brain. KELLY forces: ask → missing facts → forecast/answer → proof receipt → check-in → settlement → calibration → only then a governed memory proposal.

  1. 1Ask
  2. 2Facts
  3. 3Receipt
  4. 4Reality
  5. 5Score
  6. 6Earned memory

Sector labs are lenses. JobProof is paused. Brains are engines — not the product. Ops ceilings (Neon opt-in, soft-cap) are not densify thrash — after Railway ship: npm run accountability:post-deploy-hold.

Truth console · public scoreboard

Accountability passport

Live public Brier volume mapped to the loop. Process is not world truth. Memory remains gated.

  1. Ask
  2. Facts
  3. Receipt
  4. Reality
  5. Score
  6. Earned mem

Settled

0

Weather / Sports

0 / 0warming

Markets

0

Scale remaining

1000

SHA Posture vs_market cal Full scoreboard →

Kahneman · resulting quarantine

Settlements & score honesty

Freemium Superforecasting closes are self-reported (personal Brier only). Calibration-grade truth requires admin settle-verified with ADMIN_TOKEN. Outcome-blind process review is required before freemium scores. process_is_not_truth · never prime memory.

KELLY live pulserefreshed agolearninglifetime heartbeat 0browser pulses warmingcells 0replay-ready 0engine checkinglatest cell watchingevidence checkinglive memory laneloop: checking live activity
activity feed
Proof control room|public writes blocked|profession: proof auditor|kelly-anatomy-protocol-v1
Interactive lens

Proof auditor · Answered directly by KELLY · public writes blocked

Glass Lab · proof lens into KELLY

Settlements

Reality closure, forecast resolution, and settlement readiness for claims that need external outcome evidence.

Inspect live proof, truth debt, generation wall, and organ health. This lens does not write ground truth — KELLY remains the only write authority.

live read/api/superforecasting/kahneman-status?stakes=medium

Kahneman status (multipass posture)

System1 risk, noise multipass posture, WYSIATI — diagnostic only.

Open API
ok
true
route
/api/superforecasting/kahneman-status
live read/api/superforecasting/resolution-queue

Resolution Queue

Superforecasting settlement queue and closure obligations.

Open API
ok
true
route
/api/superforecasting/resolution-queue
queue count
0
live read/api/accountability/scoreboard

Reality Accountability Scoreboard

Public settled trail, Brier, baselines — scores only after reality closes.

Open API
ok
true
route
/api/accountability/scoreboard
live read/api/calibration/public

Public Calibration Settlements

Forward live proof settlements feeding the scoreboard (not fixtures).

Open API
ok
true
live read/api/glass-lab/reality-closure-queue

Reality Closure Queue

Claims, forecasts, and questions waiting on reality checks, replay, or calibration.

Open API
ok
true
route
/api/glass-lab/reality-closure-queue
queue count
1
live read/api/reality/status

Reality Status

Reality engine readiness for settlement and answer closure.

Open API
ok
true