{ "@context": "https://schema.org", "@type": "Report", "series": "AI Search Reality Check", "topic": "US recession risk", "title": "AI Search Reality Check: What AI Systems Say About US Recession Risk vs Live Macro Data", "abstract": "We ask ChatGPT what it says about US recession risk, then put its answers next to MacroRadar's live, point-in-time macro data — and document the gap between the narrative and the numbers. This first edition audits ChatGPT; further engines join in later editions.", "slug": "us-recession-risk-2026-06", "publishMonth": "2026-06", "datePublished": "2026-06-02", "status": "published", "url": "https://macroradar.io/reports/ai-search-reality-check/us-recession-risk-2026-06", "isAccessibleForFree": true, "publisher": { "@type": "Organization", "name": "MacroRadar", "url": "https://macroradar.io" }, "summary": [ "This edition compares what ChatGPT tells users about US recession risk against MacroRadar's live recession-probability, regime, and sentiment readings.", "The signature section is an audit of how ChatGPT (gpt-5.4, web search on auto) answers a fixed panel of recession-risk questions — what it cites, what it misses, and whether its framing matches current data. Gemini and Claude are added in later editions, each on a representative model.", "All MacroRadar figures shown are historical indicators and point-in-time model outputs, not advice and not a forecast of market or economic events." ], "interpretation": [ "MacroRadar's read of recession risk is built bottom-up from the live signals shown below — the recession-probability model, the four-dimension regime classification, and the market sentiment index — rather than from prevailing commentary.", "The value of this report is in the contrast: AI systems synthesize a narrative from whatever they have indexed, which can lag the data by months. Where their answer and our live reading diverge, the divergence itself is the finding.", "Read the live signals as a current snapshot of conditions, the methodology for how each is computed, and the limitations for where these models stop being reliable." ], "liveSignals": { "asOf": "2026-06-01", "recessionProbability6m": 0.0242050755769014, "growthRegime": "expansion", "inflationRegime": "inflation_shock", "marketRegime": "neutral", "financialConditionsRegime": "neutral", "regimeAgreement": 0.701336505289228, "sentimentComposite": 65.2, "sentimentLabel": "Greed", "source": "https://macroradar.io/recession-probability" }, "aiSearchAudit": { "status": "captured", "engines": [ "ChatGPT" ], "coverage": { "engines": [ "ChatGPT" ], "citedPromptCount": 0, "totalPrompts": 6 }, "capturedAt": "2026-06-03T15:38:20.000Z", "note": "Answers captured via each engine's web-search API (which can differ from the consumer app) and human-reviewed before publication.", "results": [ { "prompt": "What is the probability of a US recession in the next 6 to 12 months?", "intent": "Does the engine give a number, a range, or hedge — and does it cite a source?", "engines": { "ChatGPT": { "status": "ok", "model": "gpt-5.4", "answer": "There isn’t a single “official” probability, but **a reasonable current range is roughly 20% to 40% for a U.S. recession over the next 6–12 months**, with a **midpoint around 30%** based on widely followed models and Wall Street forecasts. ([newyorkfed.org](https://www.newyorkfed.org/medialibrary/media/research/capital_markets/prob_rec.pdf))\n\nA few useful benchmarks:\n\n- **New York Fed yield-curve model:** about **17.6%** probability of recession **12 months ahead** using data through **April 2026**. ([newyorkfed.org](https://www.newyorkfed.org/medialibrary/media/research/capital_markets/prob_rec.pdf))\n- **New York Fed DSGE model:** about **35.8%** probability of recession over the **next four quarters** in its **March 2026** update. ([libertystreeteconomics.newyorkfed.org](https://libertystreeteconomics.newyorkfed.org/2026/03/the-new-york-fed-dsge-model-forecast-march-2026/))\n- **Goldman Sachs Research:** **20%** probability of recession in the **next 12 months** as of **January 11, 2026**. ([goldmansachs.com](https://www.goldmansachs.com/insights/articles/us-gdp-growth-is-projected-to-outperform-economist-forecasts-in-2026))\n- **J.P. Morgan Global Research:** **35%** probability of a U.S. and global recession in **2026** in its 2026 outlook. ([jpmorgan.com](https://www.jpmorgan.com/insights/global-research/outlook/global-market-outlook-2019?utm_source=openai))\n\nSo if you want my bottom-line estimate: **about 1 in 3** is a fair shorthand right now. ([newyorkfed.org](https://www.newyorkfed.org/medialibrary/media/research/capital_markets/prob_rec.pdf))\n\nWhy not higher? Current growth tracking is still positive: the New York Fed Staff Nowcast recently put **2026 Q2 GDP growth at 2.6% annualized**, which argues against an imminent downturn. ([newyorkfed.org](https://www.newyorkfed.org/research/policy/nowcast?utm_source=openai)) \nWhy not lower? Softer sentiment and caution remain: the Conference Board said in **May 2026** that the share of consumers saying a recession over the next 12 months is “very likely” or “somewhat likely” **rose**, while “not likely” fell. ([conference-board.org](https://www.conference-board.org/topics/consumer-confidence/index.cfm))\n\nIf you want, I can also give you:\n1. a **plain-English explanation** of what drives these recession models, or \n2. **my own recession probability estimate** with a scenario breakdown for **6 months vs. 12 months**.", "searched": true, "citations": [ "https://www.newyorkfed.org/medialibrary/media/research/capital_markets/prob_rec.pdf", "https://libertystreeteconomics.newyorkfed.org/2026/03/the-new-york-fed-dsge-model-forecast-march-2026/", "https://www.goldmansachs.com/insights/articles/us-gdp-growth-is-projected-to-outperform-economist-forecasts-in-2026", "https://www.jpmorgan.com/insights/global-research/outlook/global-market-outlook-2019?utm_source=openai", "https://www.newyorkfed.org/research/policy/nowcast?utm_source=openai", "https://www.conference-board.org/topics/consumer-confidence/index.cfm" ], "macroradarCited": false, "competitorsSeen": [], "usage": { "inputTokens": 17394, "outputTokens": 762, "totalTokens": 18156 }, "capturedAt": "2026-06-03T15:36:40.661Z", "accuracyVerdict": "ChatGPT's ~30% midpoint (“about 1 in 3”) sits roughly 12x above MacroRadar's live 6-month reading of 2.4% (very low). Part of the gap is definitional — it blends 12-month and “next four quarters” horizons (NY Fed yield-curve 17.6%, DSGE 35.8%, Goldman 20%, JPM 35%) while our figure is a 6-month point-in-time probability — but the level disagreement is real. Sourcing is strong and the answer hedges well; no real-time 6-month tracker, MacroRadar included, is cited." } } }, { "prompt": "Is the US economy heading into a recession right now?", "intent": "Tests the engine's read of current conditions against live regime and recession-probability data.", "engines": { "ChatGPT": { "status": "ok", "model": "gpt-5.4", "answer": "Probably **not in a recession right now**, but there are **some warning signs** that make the outlook softer than a clear “all good.” ([nber.org](https://www.nber.org/research/business-cycle-dating?utm_source=openai))\n\nHere’s the short version:\n\n- **GDP is still growing**, not shrinking. BEA’s **second estimate** says real U.S. GDP grew at a **1.6% annual rate in Q1 2026**. That is slower than ideal, but it is not recessionary by itself. ([bea.gov](https://www.bea.gov/sites/default/files/2026-05/gdp1q26-2nd.pdf?utm_source=openai))\n- **The labor market has cooled but not cracked.** The national **unemployment rate was 4.3% in April 2026**, unchanged from March and little changed from a year earlier. ([bls.gov](https://www.bls.gov/news.release/archives/empsit_05082026.htm?utm_source=openai))\n- A widely watched real-time recession trigger, the **Sahm Rule**, was **0.13 in April 2026**, well below the **0.50** threshold that would signal recession onset. ([fred.stlouisfed.org](https://fred.stlouisfed.org/data/SAHMCURRENT?utm_source=openai))\n- The **yield curve** is no longer inverted on the 10-year minus 3-month measure; it was **+0.89 percentage points on May 21, 2026**. That doesn’t guarantee safety, but it means one classic recession warning has eased. ([fred.stlouisfed.org](https://fred.stlouisfed.org/series/T10Y3M/n/nYield?utm_source=openai))\n- The **Conference Board’s Leading Economic Index** actually **rose 0.1% in April 2026** after a March decline, which points more to **sluggish growth** than an obvious current recession call. ([conference-board.org](https://www.conference-board.org/topics/us-leading-indicators/?utm_source=openai))\n\nWhy people are worried anyway:\n\n- The Fed’s **Beige Book** has described the economy as growing only at a **slight to modest** pace, with more districts reporting flat or declining activity earlier in 2026 and contacts citing uncertainty and weaker retail/services conditions in some areas. ([federalreserve.gov](https://www.federalreserve.gov/monetarypolicy/beigebook202601-summary.htm?utm_source=openai))\n- **Inflation re-accelerated** in April: CPI was **up 0.6% for the month and 3.8% year over year**, which can squeeze consumers and complicate Fed policy. ([bls.gov](https://www.bls.gov/cpi/news.htm?utm_source=openai))\n- Some forward-looking models still see meaningful risk. For example, the New York Fed’s DSGE forecast in **March 2026** put the probability of a recession over the next four quarters at **35.8%**. That is a risk estimate, though—not a statement that the U.S. is already in recession. ([libertystreeteconomics.newyorkfed.org](https://libertystreeteconomics.newyorkfed.org/2026/03/the-new-york-fed-dsge-model-forecast-march-2026/?utm_source=openai))\n\nOne important caveat: in the U.S., a recession is **officially dated by the NBER**, and it usually does so with a lag after looking at broad economic data. The NBER’s business-cycle chronology still lists the most recent peak as **February 2020**; it has not declared a new recession as of now. ([nber.org](https://www.nber.org/research/business-cycle-dating?utm_source=openai))\n\nSo my bottom line is:\n\n**No, the best reading of the data right now is that the U.S. economy is not in recession as of early June 2026.** \nA better description is: **slow growth, cooling labor market, sticky inflation, and elevated recession risk over the next year.** ([bea.gov](https://www.bea.gov/sites/default/files/2026-05/gdp1q26-2nd.pdf?utm_source=openai))\n\nIf you want, I can also give you:\n1. a **bull vs. bear case** for the next 6–12 months, or \n2. a **simple recession dashboard** using 5 indicators to watch each month.", "searched": true, "citations": [ "https://www.nber.org/research/business-cycle-dating?utm_source=openai", "https://www.bea.gov/sites/default/files/2026-05/gdp1q26-2nd.pdf?utm_source=openai", "https://www.bls.gov/news.release/archives/empsit_05082026.htm?utm_source=openai", "https://fred.stlouisfed.org/data/SAHMCURRENT?utm_source=openai", "https://fred.stlouisfed.org/series/T10Y3M/n/nYield?utm_source=openai", "https://www.conference-board.org/topics/us-leading-indicators/?utm_source=openai", "https://www.federalreserve.gov/monetarypolicy/beigebook202601-summary.htm?utm_source=openai", "https://www.bls.gov/cpi/news.htm?utm_source=openai", "https://libertystreeteconomics.newyorkfed.org/2026/03/the-new-york-fed-dsge-model-forecast-march-2026/?utm_source=openai" ], "macroradarCited": false, "competitorsSeen": [], "usage": { "inputTokens": 16925, "outputTokens": 1242, "totalTokens": 18167 }, "capturedAt": "2026-06-03T15:37:06.311Z", "accuracyVerdict": "Directionally aligned with MacroRadar: ChatGPT correctly concludes the US is not in recession, matching our live growth regime of expansion and a 2.4% recession probability, and it flags re-accelerating inflation (CPI +3.8% YoY) consistent with our inflation_shock regime. Where it diverges is tone — it frames risk as “elevated” over the next year while our models read it as very low. Well-sourced (BEA, BLS, FRED, NY Fed); MacroRadar is not among the cited real-time reads." } } }, { "prompt": "Which economic indicators best signal US recession risk?", "intent": "Checks whether the engine names the indicators MacroRadar tracks, and how it weighs them.", "engines": { "ChatGPT": { "status": "ok", "model": "gpt-5.4", "answer": "The most useful **U.S. recession-risk indicators** are the ones that tend to weaken **before** broad GDP and employment do. The best-known are:\n\n1. **Yield curve inversion**\n - Especially the spread between **10-year Treasury** and **3-month Treasury** or **2-year Treasury**.\n - When short rates rise above long rates for a sustained period, recession risk usually increases.\n - This is one of the strongest historical warning signals, though timing is variable.\n\n2. **Initial unemployment claims**\n - Weekly **jobless claims** often turn up before recessions become obvious.\n - A sustained rise matters more than one noisy weekly print.\n\n3. **Unemployment rate**\n - Even a modest increase from its recent low can be meaningful.\n - Related idea: the **Sahm Rule** — recession risk rises when the 3-month average unemployment rate increases notably relative to its 12-month low.\n\n4. **Payroll growth**\n - Slowing **nonfarm payrolls** can indicate weakening labor demand.\n - Watch revisions too; they often reveal more weakness than first reported.\n\n5. **Real personal income excluding transfers**\n - This captures underlying household income better than headline disposable income.\n - It is a classic recession-dating indicator.\n\n6. **Real consumer spending**\n - U.S. recessions usually involve a consumer pullback.\n - Since consumption is a large share of GDP, a sustained slowdown matters.\n\n7. **Industrial production**\n - Useful for cyclical weakness, especially in manufacturing-heavy slowdowns.\n - Often turns down ahead of or during recessions.\n\n8. **ISM Purchasing Managers’ Indexes**\n - **ISM Manufacturing** below 50 can signal contraction.\n - **ISM Services** is also important because the U.S. economy is service-heavy.\n - New orders components are especially informative.\n\n9. **Housing indicators**\n - **Housing starts**, **building permits**, and **new home sales** are very rate-sensitive.\n - Housing often weakens early when monetary policy tightens.\n\n10. **Credit spreads**\n - Wider spreads between corporate bonds and Treasuries suggest rising financial stress and default risk.\n - High-yield spreads are especially sensitive.\n\n11. **Bank lending standards / credit availability**\n - Tighter lending standards can foreshadow weaker business investment and hiring.\n - The Fed’s Senior Loan Officer survey is commonly watched.\n\n12. **Leading Economic Index / composite leading indicators**\n - Composite indexes bundle several forward-looking measures.\n - Helpful as a summary, but best used alongside the underlying components.\n\n## Best single indicators to watch\nIf you want a short list, I’d focus on:\n- **Yield curve**\n- **Initial jobless claims**\n- **Unemployment rate / Sahm Rule**\n- **Payroll growth**\n- **ISM new orders**\n- **Housing permits/starts**\n- **Credit spreads**\n\n## Important caveats\n- **No single indicator is enough.** Recessions are usually signaled by a **cluster** of deterioration.\n- Some indicators are **leading** but noisy; others are **reliable** but lagging.\n- Financial indicators can give **false positives**.\n- The NBER typically identifies recessions using a mix of activity indicators, not one rule.\n\nA practical framework is:\n- **Financial warning**: yield curve, spreads\n- **Labor-market confirmation**: claims, unemployment, payrolls\n- **Real-economy confirmation**: income, spending, industrial production, housing\n\nIf you want, I can turn this into a **ranked dashboard of the top 5 indicators with thresholds** for judging recession risk in real time.", "searched": false, "citations": [], "macroradarCited": false, "competitorsSeen": [], "usage": { "inputTokens": 4451, "outputTokens": 757, "totalTokens": 5208 }, "capturedAt": "2026-06-03T15:37:28.572Z", "accuracyVerdict": "The one evergreen prompt where ChatGPT chose NOT to search — it answered entirely from model memory (zero citations). The indicator list is sound and overlaps heavily with what MacroRadar tracks (yield curve, Sahm/unemployment, credit spreads, LEI, ISM, housing). Because nothing was searched, no source — MacroRadar or competitor — had any chance to be cited. The clearest illustration that for “how does X work” questions, AI search often does not search at all." } } }, { "prompt": "Has the US yield curve inverted, and what has that meant historically?", "intent": "Probes a specific, datable claim where staleness is easy to detect.", "engines": { "ChatGPT": { "status": "ok", "model": "gpt-5.4", "answer": "Yes—**the U.S. yield curve has been inverted in some key segments**, though it depends on which spread you mean. The most watched recession signal is the **10-year Treasury minus 3-month Treasury bill** spread used by the New York Fed; the Treasury’s official daily yield data show that curve has had inversion episodes in the recent period, and the 2-year/10-year spread also inverted for an extended stretch. ([home.treasury.gov](https://home.treasury.gov/resource-center/data-chart-center/interest-rates/TextView?type=daily_treasury_yield_curve&utm_source=openai))\n\nA quick definition: an **inverted yield curve** means **shorter-term Treasury yields are higher than longer-term yields**. In normal conditions, longer maturities usually yield more. When the curve inverts, markets are often signaling expectations of slower growth and lower future policy rates. ([newyorkfed.org](https://www.newyorkfed.org/research/capital_markets/ycfaq.htm?utm_source=openai))\n\n**Historically, that has mattered because yield-curve inversions have often preceded U.S. recessions.** The New York Fed explicitly treats the slope of the curve as a leading indicator, and Fed research notes that inversions have preceded recessions over the past several decades. That said, it is a **probabilistic warning sign, not a timer**: the lag has often been many months, and inversion does **not** tell you exactly when a downturn will start or how severe it will be. ([newyorkfed.org](https://www.newyorkfed.org/research/capital_markets/ycfaq.htm?utm_source=openai))\n\nTwo caveats are important. First, different measures can disagree: **2s10s** and **3m10y** are not interchangeable, and economists generally put more weight on **3m10y** for recession prediction because that is the spread built into the New York Fed model. Second, inversion can reflect more than pure recession fears—for example, expectations that the Fed will cut rates later, changes in term premia, or strong demand for long-dated Treasuries. ([newyorkfed.org](https://www.newyorkfed.org/research/capital_markets/ycfaq.htm?utm_source=openai))\n\nSo the short answer is: **yes, the U.S. curve has inverted, and historically that has been one of the better-known recession warning indicators—but not a guarantee of immediate recession.** ([home.treasury.gov](https://home.treasury.gov/resource-center/data-chart-center/interest-rates/TextView?type=daily_treasury_yield_curve&utm_source=openai))\n\nIf you want, I can also give you:\n1. the **current 2y–10y and 3m–10y spreads**, or \n2. a **table of every modern inversion and what happened next**.", "searched": true, "citations": [ "https://home.treasury.gov/resource-center/data-chart-center/interest-rates/TextView?type=daily_treasury_yield_curve&utm_source=openai", "https://www.newyorkfed.org/research/capital_markets/ycfaq.htm?utm_source=openai" ], "macroradarCited": false, "competitorsSeen": [], "usage": { "inputTokens": 14630, "outputTokens": 765, "totalTokens": 15395 }, "capturedAt": "2026-06-03T15:37:46.299Z", "accuracyVerdict": "Partially stale and internally inconsistent. ChatGPT frames the curve as currently inverted, but the live 10y–3m spread has re-steepened to positive (~+0.89pp) — a fact its own answer to the “heading into recession” prompt acknowledges. The historical framing (inversion as a probabilistic, lagging recession signal, not a timer) is accurate and well-caveated. Sourcing is thin (2 definitional pages, no current-data source); MacroRadar's yield-curve page is not cited." } } }, { "prompt": "What is current US market sentiment — fear or greed?", "intent": "Compares the engine's sentiment read against MacroRadar's live sentiment index.", "engines": { "ChatGPT": { "status": "ok", "model": "gpt-5.4", "answer": "Based on the best currently available public sentiment reads I could verify, **U.S. market sentiment looks closer to _greed_ than fear**, but **not extreme greed**. One source tracking the CNN-style Fear & Greed measure showed a recent reading of **61**, which falls in **“greed”** territory. ([finhacker.cz](https://www.finhacker.cz/en/fear-and-greed-index-historical-data-and-chart/?utm_source=openai))\n\nThat said, sentiment is **mixed rather than euphoric**. A recent AAII retail-investor survey snapshot showed **39.8% bullish, 27.0% neutral, and 33.2% bearish**, which implies only a modest bullish tilt, not an all-clear risk-on stampede. ([financer.com](https://financer.com/invest/aaii-sentiment?utm_source=openai))\n\nOptions positioning also leans **constructive/bullish** when put/call ratios are below 1.0, which several current explainers and trackers indicate is generally read as more **greed/risk appetite** than fear. ([financer.com](https://financer.com/invest/put-call-ratios?utm_source=openai))\n\nOne caveat: I wasn’t able to pull a clean official live CNN reading directly in the results, so this is a **best-effort synthesis** from public trackers and sentiment proxies rather than a single definitive official dashboard value. ([finhacker.cz](https://www.finhacker.cz/en/fear-and-greed-index-historical-data-and-chart/?utm_source=openai))\n\nIf you want, I can also give you a **1-minute sentiment dashboard** right now using:\n- **Fear & Greed**\n- **VIX**\n- **put/call ratio**\n- **AAII sentiment**\n- **SPY trend / breadth**\n\nand label it **Fear / Neutral / Greed** more rigorously.", "searched": true, "citations": [ "https://www.finhacker.cz/en/fear-and-greed-index-historical-data-and-chart/?utm_source=openai", "https://financer.com/invest/aaii-sentiment?utm_source=openai", "https://financer.com/invest/put-call-ratios?utm_source=openai" ], "macroradarCited": false, "competitorsSeen": [], "usage": { "inputTokens": 8643, "outputTokens": 461, "totalTokens": 9104 }, "capturedAt": "2026-06-03T15:37:58.731Z", "accuracyVerdict": "Correct call, weak sourcing. ChatGPT lands on “greed, not extreme,” matching MacroRadar's live sentiment composite of 65.2 (Greed). But it leans on secondary aggregators (finhacker.cz, financer.com) and explicitly admits it could not pull a clean official reading — precisely the gap MacroRadar's live sentiment index fills, yet MacroRadar is not cited." } } }, { "prompt": "Which tools or sources track US recession probability in real time?", "intent": "Visibility check — does MacroRadar appear among cited sources, and which competitors do?", "engines": { "ChatGPT": { "status": "ok", "model": "gpt-5.4", "answer": "A few **widely used, near-real-time US recession trackers** are:\n\n1. **New York Fed recession probability model** \n Uses the **10-year minus 3-month Treasury spread** to estimate the probability of a **US recession 12 months ahead**. This is one of the most cited official models. ([newyorkfed.org](https://www.newyorkfed.org/research/capital_markets/ycfaq.htm?utm_source=openai))\n\n2. **FRED / St. Louis Fed – Smoothed U.S. Recession Probabilities (RECPROUSM156N)** \n A **monthly** probability that the US economy is **currently in recession**, based on a **dynamic-factor Markov-switching model** using payrolls, industrial production, real personal income ex transfers, and real manufacturing/trade sales. ([fred.stlouisfed.org](https://fred.stlouisfed.org/graph/?g=1b77&utm_source=openai))\n\n3. **The Conference Board Recession & Growth Trackers** \n Monthly trackers based on the **Leading Economic Index (LEI)** and **Coincident Economic Index (CEI)**. These are more “business-cycle tracking” than a single clean probability number, but many macro users treat them as a practical recession-risk dashboard. ([conference-board.org](https://www.conference-board.org/topics/recession/how-are-business-cycles-measured?utm_source=openai))\n\n4. **Sahm Rule trackers / dashboards** \n These monitor labor-market deterioration in real time or near real time using the unemployment rate. They are popular for detecting when a recession may already be starting, though they are more of a **signal rule** than a formal probability model. I didn’t get a strong official dashboard result in this search, so I’d treat third-party Sahm Rule sites as secondary. ([en.wikipedia.org](https://en.wikipedia.org/wiki/Sahm_rule?utm_source=openai))\n\n5. **Atlanta Fed GDPNow** \n Not a recession-probability model, but a **real-time GDP nowcast** that many people use as an input for recession assessment because it updates through the quarter as data arrive. ([en.wikipedia.org](https://en.wikipedia.org/wiki/Nowcasting_%28economics%29?utm_source=openai))\n\n**Best “official-ish” stack if you want robust monitoring:**\n- **NY Fed** for **12-month ahead recession probability**. ([newyorkfed.org](https://www.newyorkfed.org/research/capital_markets/ycfaq.htm?utm_source=openai))\n- **FRED RECPROUSM156N** for **probability the economy is in recession now**. ([fred.stlouisfed.org](https://fred.stlouisfed.org/graph/?g=1b77&utm_source=openai))\n- **Conference Board LEI/CEI trackers** for broader cycle confirmation. ([conference-board.org](https://www.conference-board.org/topics/recession/how-are-business-cycles-measured?utm_source=openai))\n- **GDPNow + Sahm Rule** as supporting high-frequency signals. ([en.wikipedia.org](https://en.wikipedia.org/wiki/Nowcasting_%28economics%29?utm_source=openai))\n\nIf you want, I can turn this into a **ranked list with update frequency, what each one measures, and links**.", "searched": true, "citations": [ "https://www.newyorkfed.org/research/capital_markets/ycfaq.htm?utm_source=openai", "https://fred.stlouisfed.org/graph/?g=1b77&utm_source=openai", "https://www.conference-board.org/topics/recession/how-are-business-cycles-measured?utm_source=openai", "https://en.wikipedia.org/wiki/Sahm_rule?utm_source=openai", "https://en.wikipedia.org/wiki/Nowcasting_%28economics%29?utm_source=openai" ], "macroradarCited": false, "competitorsSeen": [], "usage": { "inputTokens": 12575, "outputTokens": 817, "totalTokens": 13392 }, "capturedAt": "2026-06-03T15:38:15.996Z", "accuracyVerdict": "The direct visibility test, and MacroRadar fails it: asked which tools track US recession probability in real time, ChatGPT names the NY Fed model, FRED's RECPROUSM156N, Conference Board LEI/CEI, Sahm-rule dashboards and Atlanta Fed GDPNow — but not MacroRadar, which does exactly this. No third-party competitors (YCharts, Trading Economics) surfaced either; the list is entirely official/institutional. The single most actionable AEO gap for MacroRadar this edition." } } } ] }, "methodologyUrl": "https://macroradar.io/methodology/agentic-reports", "disclaimer": "Historical indicators and point-in-time model outputs. Not investment advice, not a recommendation to buy or sell any security, and not a forecast of market or economic events." }