A research assistant that runs the statistics for you. Ask whether crop conditions actually predict yield, or where managed money sits versus its own history — it computes the answer across 25 years of public data and draws the chart.
Try the demo →This is an actual exchange against the live data — not a mockup. Every number below is reproducible from the same public sources listed at the bottom of this page.
It predicts it, and it's the strongest relationship in our registry. Pairing the USDA national poor + very poor share during the July silking window against the WASDE US corn yield, 2008–2026:
r = −0.90 in year-over-year differences (n = 18, p < 0.0001). In levels it's r = −0.73. Differences are the more honest read — yield trends upward with genetics, so levels partly measure that trend.
| Year | Δ poor+very poor (pp) | Δ yield (bu/ac) |
|---|---|---|
| 2009 | −2.50 | 10.80 |
| 2010 | 1.50 | −11.90 |
| 2011 | 2.15 | −5.60 |
| 2012 | 25.20 | −24.10 |
| 2013 | −26.85 | 35.00 |
| 2014 | −4.50 | 12.90 |
| 2015 | 3.50 | −2.60 |
| 2016 | −3.55 | 6.20 |
| 2017 | 5.60 | 2.00 |
| 2018 | −2.80 | −0.20 |
| 2019 | 4.25 | −8.90 |
| 2020 | −5.00 | 3.90 |
| 2021 | 1.75 | 5.30 |
| 2022 | 2.60 | −3.30 |
| 2023 | 2.40 | 3.90 |
| 2024 | −4.75 | 2.00 |
| 2025 | −3.50 | 7.20 |
| 2026 | 3.50 | −3.50 |
Any two series, levels or differences, with the sample size and p-value attached. It will tell you when the answer is nothing.
Every result comes with the plot. Ask for a different window, a different pairing, or a seasonal composite and it redraws.
Where a number sits against its own history — this week's managed-money net as a percentile since 2006, not just its level.
The same data over MCP and REST, unlimited. Point Claude, ChatGPT, or your own scripts at it and skip our interface entirely.
Every weekly report and supplement stays free to read, with no account and no email. You're paying for the layer that answers questions the reports don't.
Every number traces to a public, authoritative source. Those feeds move on their own schedules, change formats, and occasionally go quiet — so every series publishes how often it should update, when it actually last did, and a live on-time / behind / stale flag. See live status →
| CFTC Disaggregated COT | Weekly positioning — producers, swap dealers, managed money. Fridays. Why it matters → |
| USDA NASS & WASDE | Crop progress and condition weekly in season; supply & demand balance sheets monthly. Crop calendar → |
| EIA | Natural gas storage, Henry Hub spot, dry gas production, power burn, LNG exports. |
| NOAA / GFS | 16-day forecast, population-weighted HDD/CDD. |
| ERA5 reanalysis | 30-year climate normals on the WMO 1991–2020 baseline. |
| US Drought Monitor | Weekly D0–D4 severity by crop region. |
Yes — all four weeklies and every supplement, no account and no email address. The subscription buys the research assistant and programmatic access to the data underneath, not the reports themselves.
The assistant can't see raw data and can't do arithmetic on it. It calls a statistics engine that computes server-side and returns the result plus its caveats, which it has to report verbatim. If a relationship isn't there, the answer comes back null — as the June control in the example above does.
Individual includes 25 a day. A full statistical analysis draws more than a simple lookup, so a day spent entirely on heavy correlations lands closer to ten. The counter resets at midnight UTC.
No. The hosted assistant runs in your browser and needs nothing installed. MCP is there if you'd rather drive the same data from Claude, ChatGPT, or your own code — it's included, unlimited, on both tiers.
No. The reports explain what each number is as they go, and the assistant answers in plain language. Knowing your way around a balance sheet helps, but nothing here assumes a trading desk.
Freely — they're public. Your API key and assistant login are single-user. Redistribution, meaning serving our data to another product's users, needs a separate agreement on any tier.