operator matrix
Live lab posture, proof, and storage in one view This is the public routing map for the KELLY organism. Labs remain specialized read-only windows; KELLY keeps write authority, central persistence, replay, proof receipts, and memory lineage.
No lab source-of-truth volumes KELLY central writes
KELLY only
Public labs inspect, ask, forecast, and explain without writing ground truth.
Central Neon
Proof, replay, forecast, settlement, memory, and lineage stay in KELLY read models.
0 required
Standalone labs do not need source-of-truth Railway volumes.
Glass Lab
Every lab row points back to its public proof shelf.
Lab Live status Proof Storage posture Write boundary Actions
Ask KELLY
Conversation
Conversation and decision help
operational lens
central read model 64%
answer chain
Shows the answer chain without letting a public user write ground truth.
Open Glass Lab proof Postgres
Optional private user/session store only
Volume
No ground-truth volume
Browser-local watched context plus sanitized intent
Boundary
No KELLY memory, GraphState, settlement, or source writes
Superforecasting
Forecast scoring
Forecast discipline and scoring
operational lens
central read model 82%
calibration lane
Keeps user probability separate from KELLY probability so calibration stays honest.
Open Glass Lab proof Postgres
Central forecast, settlement, and calibration read models
Volume
No ground-truth volume
Separated user and KELLY forecast lanes
Boundary
User forecasts remain separate from KELLY truth
Markets Lab
Markets
Market forecast lens
operational lens
central read model 78%
market proof
Every visible forecast should point back to source, timestamp, model posture, and settlement status.
Open Glass Lab proof Postgres
API-first central quote, forecast, and source receipts
Volume
No ground-truth volume
Immutable source receipts through KELLY proof spine
Boundary
Read-only analysis; no trade execution or truth writes
Glass Lab
Transparency
Full transparency console
operational lens
central read model 96%
live proof index
This is the live window into receipts, replay, event ledger, memory, calibration, authority, and link health.
Open Glass Lab proof Postgres
Direct-first read-only proof and replay views
Volume
No ground-truth volume
R2/object evidence and central event receipts
Boundary
Observer console only; KELLY writes internally
Betting and Odds Lab
Probability
Odds and sports probability
operational lens
central read model 76%
odds settlement
Every visible forecast points back to odds snapshot, probability conversion, and outcome receipt when available.
Open Glass Lab proof Postgres
API-first odds snapshots and settlement receipts
Volume
No ground-truth volume
Immutable odds/source receipts through KELLY
Boundary
Read-only probability analysis; no bet execution
Weather and Disaster Lab
Hazards
Place and hazard awareness
operational lens
central read model 74%
weather closure
Every snapshot names source freshness, place authority, and the closure path back to Glass Lab.
Open Glass Lab proof Postgres
API-first hazard, alert, and source-freshness read models
Volume
No ground-truth volume
Object evidence for alerts, maps, and receipt bundles
Boundary
Awareness window only; not emergency instruction
Policy and Economics Lab
Public records
Public records and macro signals
operational lens
central read model 80%
citation record
Every claim should tie to citations, effective dates, and source authority.
Open Glass Lab proof Postgres
API-first public-record and macro signal read models
Volume
No ground-truth volume
Source citations, effective dates, and immutable records
Boundary
Read-only research; no legal or tax authority
Science and Research Lab
Research
Evidence and research reasoning
operational lens
central read model 84%
evidence lattice
Every research claim should expose source metadata and falsification posture.
Open Glass Lab proof Postgres
Scoped science evidence and falsifier read models
Volume
No ground-truth volume
Paper metadata, contradiction receipts, and source bundles
Boundary
Research support only; no public truth approval
Hypothesis Lab
Discovery
KELLY-generated questions
operational lens
central read model 88%
unknown ledger
Every hypothesis should expose falsifier, source plan, settlement target, and replay path.
Open Glass Lab proof Postgres
Direct-first unknown, hypothesis, and source-plan views
Volume
No ground-truth volume
Falsifier and closure receipts linked to Glass Lab
Boundary
Public users cannot approve memory or GraphState writes
Memory and Lineage Lab
Memory
Memory ancestry and repair
operational lens
central read model 94%
cell lineage
Every cell should connect to its replay receipt, lineage, and quarantine posture.
Open Glass Lab proof Postgres
Direct-first memory, replay, lineage, and quarantine views
Volume
No ground-truth volume
Birth-to-root cell dossiers and immutable replay bundles
Boundary
Memory writes are internal KELLY authority only
Ask KELLY Decision advisor
Briefing desk · conversation
Turn a plain-language question into a bounded decision: act, wait, or test — with uncertainty and proof one click away.
Primary instrument
answer contract
Success criteria
User leaves with next action, unacceptable risk, and an honest watch state — not fake certainty.
Ask a real question, then save it as a watched question if the answer needs future evidence.
Shows the answer chain without letting a public user write ground truth.
Superforecasting Superforecaster
Probability workbench · workbench
Frame measurable events, pre-commit dual probabilities, settle against reality, and score calibration.
Primary instrument
probability + settlement
Success criteria
Every forecast has event, horizon, dual lanes, resolver, and a path to Brier/reliability scoring.
Turn an uncertain future event into a forecast with a closing condition and settlement date.
Keeps user probability separate from KELLY probability so calibration stays honest.
Markets Lab Market analyst
Market terminal · terminal
Read quote tape with freshness first, forecast cones with uncertainty, paper score — never trade execution.
Primary instrument
quote freshness
Success criteria
Analyst sees source time, cone, macro context, paper P&L, and proof before any chart drama.
Pick a tracked asset and inspect the source, forecast posture, proof link, and paper P&L.
Every visible forecast should point back to source, timestamp, model posture, and settlement status.
Glass Lab Proof auditor
Proof control room · control room
Public trust console: receipts, replay, organ health, truth debt, generation wall, and no-write boundary.
Primary instrument
live proof index
Success criteria
Skeptic can verify live proof, spot debt/gaps, open any artifact trail, confirm public writes blocked.
Start with the Learning Loop Passport, then open the feed worker, Prime queue, and replay panels.
This is the live window into receipts, replay, event ledger, memory, calibration, authority, and link health.
Betting and Odds Lab Sports probability analyst
Sports probability trading desk · workbench
Convert live book lines to fair implied probability, measure KELLY disagreement, score after game close — never place bets for the user.
Primary instrument
implied vs KELLY
Success criteria
Implied % vs KELLY % is explicit, line age is timed, settlement publishes Brier customers can audit.
Choose a market and inspect whether KELLY sees a meaningful probability divergence.
Every visible forecast points back to odds snapshot, probability conversion, and outcome receipt when available.
Weather and Disaster Lab Hazard intelligence officer
Emergency-operations style awareness board · operations
Place-aware weather and disaster windows with official source freshness, alerts, and observed closure — not emergency command authority.
Primary instrument
hazard window
Success criteria
Place, hazard priority, source time, alert posture, and closure path are all visible before any risk claim.
Check weather and disaster risk near you — proof-backed reads from NOAA and NWS.
Every snapshot names source freshness, place authority, and the closure path back to Glass Lab.
Policy and Economics Lab Policy & records researcher
Public-records research desk · workbench
Start with official citations and effective dates, then macro signals — never partisan framing or legal advice.
Primary instrument
citation + effective date
Success criteria
Citation, effective date, affected scope, and falsifier plan precede any causal thesis.
Ask which public records changed and what would falsify the policy thesis.
Every claim should tie to citations, effective dates, and source authority.
Science and Research Lab Research evidence auditor
Evidence lattice · workbench
Map claim support, contradiction, recency, and falsifiers — evidence quality over volume.
Primary instrument
claim audit
Success criteria
Every claim shows support, contradiction pressure, source quality, and what would break it.
Pick a claim and inspect what evidence would strengthen or break it.
Every research claim should expose source metadata and falsification posture.
Hypothesis Lab Theory builder
Hypothesis forge · workbench
Turn observations into falsifiable questions with source plans and closure targets.
Primary instrument
falsifiable question
Success criteria
No hypothesis ships without falsifier, source plan, and reality watcher.
Open the highest-value hypothesis and inspect what would change KELLY's mind.
Every hypothesis should expose falsifier, source plan, settlement target, and replay path.
Memory and Lineage Lab Memory lineage archivist
Provenance archive · archive
Trace birth-to-root ancestry, generation walls, supersession, quarantine, and repair eligibility.
Primary instrument
generation wall
Success criteria
Any cell shows parent, generation, ancestry edge, replay posture, and repair state.
Pick a cell and trace its parent, receipt, replay state, and eligibility.
Every cell should connect to its replay receipt, lineage, and quarantine posture.
