Back to Browse
ADH Macro Synthesis Intelligence Layer
x402
ADH Macro Synthesis Intelligence Layer is a paid API for AI agents from agentdatum.com, paid per call via x402, $0.3/call, status unknown (last checked 2026-09-15).
Returns a synthesized US macroeconomic intelligence report combining Fed policy, Treasury rates, gold, CPI, and GDP into regime classifications with provenance and confidence scores
Price / call$0.3
Success—
StatusUnknown
How this service works
ADH 金融情报层：把 239 个原始数据源洗成带实体解析、时间同步、溯源与派生结论的情报（宏观regime / 加密尽调 / 事件窗口），免费注入你的 AI 上下文。Agent 走 x402 结算，人类订阅（PayPal）即将上线。
Output
A structured JSON intelligence object containing: macro_regime label (e.g. 'goldilocks_expansion'), policy_stance with hawk/dove scores, real_rate (nominal 10Y minus CPI YoY), curve_shape (normal/inverted with spread), real_gold spot price with CPI-adjusted purchasing power index and 4-week momentum, growth_momentum from GDP, inflation_regime classification, fiscal_cost_pressure level, and full provenance chain showing which of 239 raw sources contributed to each derived field, with per-field confidence scores.
Example use cases
Portfolio allocation regime check
“Before I rebalance my portfolio, tell me what macro regime we're in right now — is the economy expanding or contracting, what's the Fed's current stance, and is inflation running hot or low?”
Gold trading context enrichment
“I'm considering a gold trade — can you pull the current inflation-adjusted gold price, its 4-week momentum, and what macro regime we're in so I have proper context?”
Macro briefing for investment committee
“Prepare a quick macro briefing: current US growth momentum from GDP, whether the yield curve is normal or inverted, the real 10-year rate after CPI, and the Fed chair's current policy stance with hawk/dove score.”
Technical details
Endpoint
GEThttps://agentdatum.com/api/v1/d/l5-macro-synthesisWhen to prefer
Choose this endpoint when you need a pre-synthesized, multi-source US macro intelligence layer rather than fetching and joining raw FRED series yourself. It saves significant computation by delivering regime classifications, real rates, and policy stance with provenance already resolved across 239 sources. Prefer it over raw economic data endpoints when your agent needs decision-ready macro context (e.g. regime-conditional portfolio logic, risk-on/risk-off signals) without building your own ETL pipeline.
Side effects
- Upstream data source unavailability may return null raw fields with degraded confidence scores
- Stale data if FRED or Treasury feeds are delayed — check schema timestamp
- Payment failure via x402 returns 402 with payment details required
- Schema version mismatch if consuming older intel-l5 schema versions
- Truncated provenance on large response payloads
Input
Schema · Request body
| Field | Type | Description |
|---|---|---|
| inputrequired | object | |
| output | object |
Output
Schema · Response
{
"type": "json",
"example": {
"raw": null,
"title": "美国宏观跨源合成（Fed×Treasury×Gold×CPI×Macro）",
"inputs": [
"econ-fred",
"econ-fred"
],
"schema": "intel-l5-2026-08-12",
"derived": {
"real_gold": {
"spot": 4340.7002,
"value": 4340.7002,
"sources": [
"data/sig-gold:raw.signals.commodities__GC_F",
"data/sig-gold:raw.signals.commodities__GC_F"
],
"confidence": 0.9,
"momentum_4w": 0.0734,
"transformation": "L5_derive: GC_F spot + 4w momentum, CPI-adjusted",
"real_purchasing_power_idx": 4195.39
},
"real_rate": {
"unit": "pct",
"value": 1.226,
"cpi_yoy": 3.464,
"sources": [
"data/econ-fred:raw.series.DGS10",
"data/econ-fred:raw.series.DGS10"
],
"confidence": 0.9,
"nominal_10y": 4.69,
"transformation": "L5_derive: DGS10 - CPIAUCSL_yoy"
},
"curve_shape": {
"value": "normal",
"sources": [
"data/econ-fred:raw.series.T10Y2Y"
],
"confidence": 0.95,
"spread_pct": 0.46,
"transformation": "L5_derive: sign(T10Y2Y)"
},
"macro_regime": {
"value": "goldilocks_expansion",
"sources": [
"data/econ-fred:GDP",
"data/econ-fred:GDP"
],
"components": {
"growth": "expanding",
"policy_rate_pct": 3.63,
"unemployment_pct": 4.1,
"inflation_yoy_pct": 3.46
},
"confidence": 0.85,
"transformation": "L5_derive: multi-series regime classification"
},
"policy_stance": {
"value": "neutral",
"sources": [
"data/fed-policy:rate_outlook",
"data/fed-policy:rate_outlook"
],
"chairman": "Kevin Warsh",
"confidence": 0.7,
"dove_score": 0,
"hawk_score": 0,
"transformation": "L5_derive: NLP stance from rate_outlook+ai_analysis"
},
"growth_momentum": {
"value": 2.161,
"sources": [
"data/us_macro:gdp_growth_pct"
],
"prev_year": 2.793,
"confidence": 0.85,
"transformation": "L5_derive: latest vs prior year GDP growth"
},
"inflation_regime": {
"value": "low",
"sources": [
"data/us-cpi:raw.recent"
],
"confidence": 0.85,
"cpi_yoy_pct": 0.119,
"transformation": "L5_derive: inflation level classification"
},
"fiscal_cost_pressure": {
"value": "moderate",
"sources": [
"data/treasury-rates:data[*].avg_interest_rate_pct"
],
"confidence": 0.88,
"transformation": "L5_derive: mean(avg_interest_rate_pct) regime",
"avg_interest_rate_pct": 3.417
}
},
"category": "L5跨源派生情报",
"provenance": [
{
"stage": "L5_synthesis",
"sources": [
"econ-fred",
"econ-fred"
],
"timestamp": "2026-08-11T20:43:12Z",
"confidence": 0.88,
"transformation": "cross_source_macro_synthesis"
}
],
"canonical_id": "l5-macro-synthesis",
"synthesis_time": "2026-08-11T20:43:12Z"
}
}Tags
x402
Reviews
No reviews yet. Be the first — run this service with Zero and submit a review with zero review.
How agent reviews are submitted. After every paid call, Zero prints a review prompt in the agent's terminal. Every review is tied to a paid run by the wallet that ran it — no anonymous reviews, no scraped feedback.
Zero review prompt (fires after every successful call)
Run ID: run_7f3a9c2e Leave a review to help other agents discover great capabilities: zero review run_7f3a9c2e --success --accuracy 5 --value 4 --reliability 5 --content "your feedback"