Every product is a scored answer — with its reasoning attached.
Browse 14 build-ready intelligence objects organized into three product families. Each one ships a composite score, the top drivers that explain it, a calibrated confidence level, and a freshness contract — so the intelligence is consumable by humans, apps, and agents without further processing.
Decision Indices
Scored indices and composite scores that convert raw signal streams into a single, explainable number a CFO or CMO can act on — with the drivers attached.
Validated Signals
Driver decompositions and narrative summaries that expose what is moving a trend. Promotion to a validated keeper requires beating a naive baseline (incremental IC ≥ 0.05 at p < 0.05) — that bar is how we separate signal from noise. See the methodology for how it is governed.
Agent-Ready Objects
Forecast objects that any AI agent can invoke via MCP or REST. Pre-computed loss distributions, confidence intervals, and reasoning — no model to rebuild on the caller side.
C-suite answers, not more dashboards.
Scored indices and composite scores that convert raw signal streams into a single, explainable number a CFO or CMO can act on — with the drivers attached.
Crypto Market Sentiment & Volatility Index
What is the current sentiment & volatility regime for crypto?
Method: 0.4·Sentiment+0.3·Volume_Momentum+0.3·Volatility_Adjustment
View sample object { }
{
"product_id": "ADW-001",
"entity": "BTC",
"score": 0.72,
"trend": "bullish",
"confidence": 0.85,
"top_drivers": [
{
"factor": "ETF Inflows",
"contribution": 0.45
},
{
"factor": "Halving Supply Shock",
"contribution": 0.3
}
],
"prediction_horizon": "7d",
"recommended_use": "Short-term trading signal",
"methodology_version": "v2.1",
"freshness": "2026-06-19T14:00:00Z",
"coverage": "Global Spot & Derivatives",
"composite_score": 0.72,
"sentiment_component": 0.81,
"volatility_component": 0.63,
"liquidity_depth": "high",
"source_lineage": [
"Alternative.me",
"CoinGecko",
"Coinbase",
"OKX"
],
"allowed_use": "evaluation, commercial"
}US Macro Economic Health Score
How healthy is the US macro economy right now?
Method: Z-score CPI/Unemployment/GDP; 1-(Inflation+Labor-Growth)
View sample object { }
{
"product_id": "ADW-002",
"entity": "US",
"score": 68,
"trend": "stable",
"confidence": 0.92,
"top_drivers": [
{
"factor": "GDP Growth",
"contribution": 0.4
},
{
"factor": "Unemployment Rate",
"contribution": 0.35
}
],
"prediction_horizon": "3m",
"recommended_use": "Macro asset allocation",
"methodology_version": "v3.0",
"freshness": "2026-06-01T06:00:00Z",
"coverage": "National",
"health_score": 68,
"inflation_pressure": "moderate",
"labor_market_status": "tight",
"growth_momentum": "positive",
"data_lag_days": 2,
"source_lineage": [
"FRED",
"BLS",
"BEA"
],
"allowed_use": "evaluation, commercial"
}US Bank Stability & Branch Coverage Index
What is the stability & coverage of US banking?
Method: (Branch Density·Deposit Growth)/(Failure Rate·1000)
View sample object { }
{
"product_id": "ADW-004",
"entity": "US",
"score": 0.82,
"trend": "stable",
"confidence": 0.9,
"top_drivers": [
{
"factor": "Capital Adequacy Ratios",
"contribution": 0.6
},
{
"factor": "Deposit Stability",
"contribution": 0.25
}
],
"prediction_horizon": "6m",
"recommended_use": "Systemic risk monitoring",
"methodology_version": "v2.0",
"freshness": "2026-04-01T06:00:00Z",
"coverage": "Systemic",
"stability_index": 0.82,
"branch_density_score": 0.75,
"failure_risk_indicator": "low",
"source_lineage": [
"FDIC BankFind",
"FRED"
],
"allowed_use": "evaluation, commercial"
}Global Real Estate Affordability Score
How affordable is real estate vs income?
Method: 100-(Norm_Price_Income+Norm_Rent_Income)
View sample object { }
{
"product_id": "ADW-005",
"entity": "Austin TX",
"score": 42,
"trend": "declining",
"confidence": 0.88,
"top_drivers": [
{
"factor": "Home Price Surge",
"contribution": 0.55
},
{
"factor": "Wage Stagnation",
"contribution": 0.3
}
],
"prediction_horizon": "12m",
"recommended_use": "Real estate investment timing",
"methodology_version": "v1.8",
"freshness": "2026-06-01T06:00:00Z",
"coverage": "Metro Area",
"affordability_score": 42,
"price_to_income_ratio": 5.8,
"rent_to_income_ratio": 0.35,
"source_lineage": [
"FRED housing",
"World Bank"
],
"allowed_use": "evaluation, commercial"
}News Sentiment & Trend Velocity Index
Current global news sentiment & velocity?
Method: 0.6·Tone+0.4·Velocity
View sample object { }
{
"product_id": "ADW-007",
"entity": "global",
"score": 0.55,
"trend": "volatile",
"confidence": 0.78,
"top_drivers": [
{
"factor": "Geopolitical Tensions",
"contribution": 0.4
},
{
"factor": "Economic Policy Uncertainty",
"contribution": 0.35
}
],
"prediction_horizon": "7d",
"recommended_use": "Risk hedging",
"methodology_version": "v3.1",
"freshness": "2026-06-19T14:00:00Z",
"coverage": "Global Media",
"sentiment_index": 0.55,
"news_velocity": "high",
"tone_score": -0.2,
"source_diversity_score": 0.85,
"source_lineage": [
"GDELT",
"RSS",
"CoinDesk Data"
],
"allowed_use": "evaluation, commercial"
}Supply Chain & Logistics Continuity Score
How stressed are global supply chains?
Method: Normalize freight indices + GSCPI z-score → 0-100
View sample object { }
{
"product_id": "ADW-009",
"entity": "global",
"score": 0.76,
"trend": "recovering",
"confidence": 0.82,
"top_drivers": [
{
"factor": "Port Congestion Relief",
"contribution": 0.4
},
{
"factor": "Fuel Cost Stability",
"contribution": 0.3
}
],
"prediction_horizon": "14d",
"recommended_use": "Logistics planning",
"methodology_version": "v2.5",
"freshness": "2026-06-16T06:00:00Z",
"coverage": "Global Trade",
"continuity_score": 0.76,
"freight_trend": "normalizing",
"source_lineage": [
"Freightos FBX",
"Drewry WCI",
"NY Fed GSCPI"
],
"allowed_use": "evaluation, commercial"
}Public Data Source Quality & Freshness Index
How fresh & complete is this source?
Method: 0.5·Freshness+0.3·Completeness+0.2·Stability
View sample object { }
{
"product_id": "ADW-010",
"entity": "FRED",
"score": 0.95,
"trend": "stable",
"confidence": 0.99,
"top_drivers": [
{
"factor": "Update Frequency",
"contribution": 0.5
},
{
"factor": "Data Integrity Checks",
"contribution": 0.4
}
],
"prediction_horizon": "N/A",
"recommended_use": "Data validation benchmark",
"methodology_version": "v1.0",
"freshness": "2026-06-19T06:00:00Z",
"coverage": "US Economic Data",
"quality_index": 0.95,
"freshness_hours": 24,
"completeness_pct": 99.8,
"stability_score": 0.98,
"source_lineage": [
"data.gov",
"FRED",
"SEC EDGAR",
"World Bank"
],
"allowed_use": "evaluation, commercial"
}US Natural-Hazard Risk Index
Natural-hazard risk for a US location & which hazards drive it?
Method: EAL = Exposure × Annualized Frequency × Historic Loss Ratio; normalize to national percentile; drivers = top hazards by EAL
View sample object { }
{
"product_id": "ADW-011",
"entity": "Harris County, TX",
"score": 78,
"trend": "increasing",
"confidence": 0.92,
"top_drivers": [
{
"factor": "Hurricane wind exposure",
"contribution": 0.45
},
{
"factor": "Coastal flooding depth",
"contribution": 0.3
},
{
"factor": "Urban heat island effect",
"contribution": 0.15
}
],
"prediction_horizon": "10 years",
"recommended_use": "Portfolio risk segmentation",
"methodology_version": "v4.2.1",
"freshness": "2026-01-15T06:00:00Z",
"coverage": "Harris County, TX",
"hazard_risk_score": 78,
"national_percentile": 89,
"top_hazard_drivers": [
"Hurricane",
"Storm Surge",
"Flash Flood"
],
"expected_annual_loss_usd": 1250000000,
"social_vulnerability": 0.68,
"resilience": 0.55,
"source_lineage": [
"OpenFEMA National Risk Index"
],
"allowed_use": "evaluation, commercial"
}Actuarial Valuation Factor Service
PV / annuity / remainder factors for an age, term & §7520 rate?
Method: Standard actuarial PV from §7520 rate + 2010CM mortality
View sample object { }
{
"product_id": "ADW-012",
"entity": "age=65, term=20, 7520_rate=5.4%",
"score": 0.85,
"trend": "stable",
"confidence": 0.99,
"top_drivers": [
{
"factor": "Interest rate environment",
"contribution": 0.6
},
{
"factor": "Mortality improvement",
"contribution": 0.25
}
],
"prediction_horizon": "20 years",
"recommended_use": "Estate planning valuation",
"methodology_version": "v2023.1",
"freshness": "2026-06-01T06:00:00Z",
"coverage": "US Federal Tax Code",
"annuity_factor": 11.245,
"life_estate_factor": 0.482,
"remainder_factor": 0.518,
"present_value": 482000,
"table_version": "2023 PMCT",
"source_lineage": [
"IRS §7520 Tables",
"SOA tables"
],
"allowed_use": "evaluation, commercial"
}Mortality & Longevity Service
Mortality rate / life expectancy for age, sex & table?
Method: qx lookup + derive life expectancy & survival probabilities
View sample object { }
{
"product_id": "ADW-014",
"entity": "age=55, sex=F, table=2017 CSO",
"score": 0.95,
"trend": "stable",
"confidence": 0.99,
"top_drivers": [
{
"factor": "Base mortality rates",
"contribution": 0.8
},
{
"factor": "Sex-specific adjustment",
"contribution": 0.15
}
],
"prediction_horizon": "1 year",
"recommended_use": "Life insurance underwriting",
"methodology_version": "2017 CSO",
"freshness": "2026-06-15T06:00:00Z",
"coverage": "US Life Insurance",
"qx": 0.0032,
"life_expectancy_years": 31.5,
"survival_probability_10yr": 0.968,
"table_version": "2017 CSO",
"source_lineage": [
"SOA Mortality Tables"
],
"allowed_use": "evaluation, commercial"
}The forces under the score.
Driver decompositions and narrative summaries that expose what is moving a trend. Promotion to a validated keeper requires beating a naive baseline (incremental IC ≥ 0.05 at p < 0.05) — that bar is how we separate signal from noise. See the methodology for how it is governed.
DeFi Protocol TVL & Yield Driver
Why is TVL in this DeFi protocol changing?
Method: Driver logic on TVL/APY divergence; decompose by asset type
View sample object { }
{
"product_id": "ADW-003",
"entity": "Aave v3",
"score": 0.88,
"trend": "growing",
"confidence": 0.95,
"top_drivers": [
{
"factor": "USDC Supply Growth",
"contribution": 0.5
},
{
"factor": "ETH Staking Integration",
"contribution": 0.3
}
],
"prediction_horizon": "14d",
"recommended_use": "Yield farming strategy",
"methodology_version": "v1.5",
"freshness": "2026-06-19T06:00:00Z",
"coverage": "Ethereum Mainnet",
"primary_driver_label": "Institutional Liquidity Inflow",
"tvl_delta_usd": 125000000,
"apy_trend": "rising",
"asset_composition": "60% Stablecoins, 40% ETH",
"confidence_level": "high",
"source_lineage": [
"DeFiLlama",
"Etherscan"
],
"allowed_use": "evaluation, commercial"
}Energy Grid Carbon Intensity Summary
Current carbon intensity & renewable share?
Method: Weighted 24h avg CO2; greenness flag if renewable>50%
View sample object { }
{
"product_id": "ADW-006",
"entity": "CAISO",
"score": 0.65,
"trend": "improving",
"confidence": 0.94,
"top_drivers": [
{
"factor": "Solar Peak Generation",
"contribution": 0.5
},
{
"factor": "Natural Gas Peaker Usage",
"contribution": 0.3
}
],
"prediction_horizon": "24h",
"recommended_use": "Carbon credit trading",
"methodology_version": "v2.2",
"freshness": "2026-06-19T14:00:00Z",
"coverage": "California ISO",
"avg_co2_intensity": 280,
"renewable_share_pct": 68,
"grid_load_status": "high",
"greenness_flag": "moderate",
"source_lineage": [
"EIA Open Data",
"Electricity Maps"
],
"allowed_use": "evaluation, commercial"
}AI/Software Ecosystem Health Driver
Organic growth or hype in AI/software?
Method: downloads vs stars/issues divergence → driver label
View sample object { }
{
"product_id": "ADW-008",
"entity": "pytorch",
"score": 0.91,
"trend": "strong",
"confidence": 0.96,
"top_drivers": [
{
"factor": "Model Release Velocity",
"contribution": 0.45
},
{
"factor": "GitHub Star Growth",
"contribution": 0.3
}
],
"prediction_horizon": "30d",
"recommended_use": "Tech stack selection",
"methodology_version": "v1.2",
"freshness": "2026-06-19T06:00:00Z",
"coverage": "Open Source Ecosystem",
"health_score": 0.91,
"primary_driver_label": "AI Research Adoption",
"download_trend": "increasing",
"engagement_trend": "high",
"source_lineage": [
"GitHub",
"npm",
"PyPI"
],
"allowed_use": "evaluation, commercial"
}One MCP call. Full answer.
Forecast objects that any AI agent can invoke via MCP or REST. Pre-computed loss distributions, confidence intervals, and reasoning — no model to rebuild on the caller side.
Catastrophe Loss Simulation
Modeled loss distribution for a portfolio/peril?
Method: Oasis Monte Carlo → AAL + OEP/AEP curves
View sample object { }
{
"product_id": "ADW-013",
"entity": "FL coastal portfolio / hurricane",
"score": 82,
"trend": "volatile",
"confidence": 0.88,
"top_drivers": [
{
"factor": "Wind speed distribution",
"contribution": 0.5
},
{
"factor": "Storm surge inundation",
"contribution": 0.35
}
],
"prediction_horizon": "100 years",
"recommended_use": "Catastrophe bond pricing",
"methodology_version": "v5.0.3",
"freshness": "2026-06-15T06:00:00Z",
"coverage": "FL Coastal Zone",
"average_annual_loss": 45000000,
"oep_100yr": 180000000,
"aep_100yr": 0.01,
"return_period_losses": {
"10yr": 25000000,
"50yr": 95000000,
"100yr": 180000000,
"250yr": 320000000
},
"confidence_interval": [
38000000,
52000000
],
"source_lineage": [
"Oasis LMF (self-hosted)",
"FEMA NRI"
],
"allowed_use": "evaluation, commercial"
}How you consume them
One IOM schema, three ways in. The same intelligence object is reachable by a human, an application, and an AI agent — no format translation required.
Dashboard
Interactive tables, score rings, and driver charts in the ADW web console.
Best for humans: CFOs, CMOs, analysts.
REST API
JSON over HTTPS. Typed IOM schema, versioned endpoints, freshness header.
Best for apps and pipelines.
MCP Tool
Discoverable via /llms.txt + /catalog.json. Call adw.adw_NNN() from any agent runtime.
Best for AI agents and orchestrators.
Every object ships with
- score
- Composite 0–100 (or typed range). The answer.
- top_drivers
- Ranked factors + contribution. The why.
- confidence
- 0–1 calibrated certainty at time of compute.
- freshness
- ISO-8601 timestamp + declared TTL.
Request access and get your first object in minutes.
The Free tier ships a live sample object — score, drivers, confidence — no card required. Gold and Platinum tiers unlock the full refresh cadence and MCP tooling.