ask kelly
Truth: evidence_partial
2026 product definition
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.
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
Live public Brier volume mapped to the loop. Process is not world truth. Memory remains gated.
Settled
0
Weather / Sports
0 / 0warming
Markets
0
Scale remaining
1000
Proof auditor · Answered directly by KELLY · public writes blocked
Glass Lab · proof lens into KELLY
Glass Lab is the proof console — layered, inspectable trail of why KELLY acted; gaps and organ maturity stay honest.
Inspect live proof, truth debt, generation wall, and organ health. This lens does not write ground truth — KELLY remains the only write authority.
proof gaps open
26
proof gaps blockers
1
lenses evolving
7
lenses completion claimed
0
truth wall waiting
25
fixture like domain receipts
0
independent attestations
0
layer b ready domains
0
rgi runtime mode
live_governed
live default promotion active
ask kelly
Truth: evidence_partial
superforecasting
Truth: settlement_pending
glass lab
Truth: visible_in_glass_lab
reality accountability
Truth: settled_world_only
Claim strength
Level 4
Observatory routes
Evolving lens snapshot
Full lens wall →Science and Research Lab
evidence falsification organ
source
40%
proof
32%
settlement
6%
calibration
0%
Memory and Lineage Lab
memory replay lineage organ
source
37%
proof
29%
settlement
3%
calibration
0%
Hypothesis Lab
hypothesis falsification organ
source
34%
proof
26%
settlement
0%
calibration
0%
Weather and Disaster Lab
domain lens weather
source
31%
proof
23%
settlement
0%
calibration
0%