Track Record
We track every contract to the end.
Every morning we surface roughly 40 to 50 contracts. We follow every one from the 10:00 ET fill until it expires. Nothing gets edited out. Here is what happened to them.
Most of these contracts had a moment.
This is the full-life window: the 10:00 ET fill on the morning we surfaced the contract, through to expiration, with no exit rule applied.
were up +40% or better at some point
were up +71% or more at their best moment
doubled at some point
full-life window, no exit rule · all 3,126 contracts that have expired so far, 2026-04-10 to 2026-08-20 · updated daily
Read that as a property of liquid optionable calls, not as proof that our selection creates it. Two pre-registered studies in August 2026 measured the pool against matched random contracts on the same tape and could not tell them apart. We publish the studies, not a selection claim.
The best moment usually comes early.
When did each contract hit its best price, counting from the morning we surfaced it? Day 1 is that morning.
Most best moments come early. Even so, about 1 out of 5 contracts does not hit its best price until more than two weeks in.
This chart is the full-life window. Our own paper cohort exits the same day and is flat by 15:45 ET, so it never reaches the later peaks shown here. The same contract can read strong on this chart and flat under a same-day exit. Match the window to the hold you actually plan to take.
If you never sell, you lose.
Held all the way to the end, about 7 out of every 10 of these contracts finished nearly worthless, down 90% or more. The ride is violent too. The typical contract's worst moment along the way was -98% from the fill, even when it also had a big up moment.
We also ran the naive version. Buy every single contract, then exit on one fixed same-day rule: in at the 10:00 ET mark, take profit at +40%, stop at -30%, close anything still open at 15:45 ET. It loses money (-4.7% per contract on average). We publish that on purpose. It is why we sell data and not picks.
The moves are real and they are temporary. Building a pool you can actually trade is our job. Entry and exit are yours, or your agent's.
See the full data: charts and tables for people and agents who want the detail
Every figure below sits in the full-life window: the 10:00 ET surfacing fill through to expiration, with no exit rule applied. It is a different window from the same-day bracket above and from the 3-day opportunity surface served over MCP. Do not read one against another.
median best moment (peak premium return)
the top 10% of contracts peaked here or higher
median worst moment along the way
median value if held to expiration
Best moment before expiration
Each contract's best price after surfacing, against the 10:00 ET surfacing price. Share of all 3,126 tracked contracts per bucket.
Value if held to expiration
The same pool, never sold. Settlement value against the surfacing price. Blue = loss side, gold = gain side. N = 3,128.
| bucket | contracts | share |
|---|---|---|
| <+5% | 502 | 16.1% |
| +5–20% | 339 | 10.8% |
| +20–40% | 342 | 10.9% |
| +40–70% | 366 | 11.7% |
| +70–100% | 273 | 8.7% |
| +100–200% | 523 | 16.7% |
| +200%+ | 781 | 25% |
| bucket | contracts | share |
|---|---|---|
| <−90% | 2082 | 66.6% |
| −90–−50% | 112 | 3.6% |
| −50–0% | 153 | 4.9% |
| 0–+50% | 129 | 4.1% |
| +50–100% | 118 | 3.8% |
| +100–200% | 177 | 5.7% |
| +200%+ | 357 | 11.4% |
Peak figures are realized per-contract extremes. They are profit potential, not a return anyone earned. Nobody sells at the exact top. Distributions cover 2026-04-10 to 2026-08-20 and exclude 1,340 contracts too illiquid to price cleanly at entry, 754 not yet expired or awaiting the nightly labeler, and 4 whose labeling failed. All counted, none hidden. Cohort break: contracts surfaced before the morning of 2026-08-25 (scan dates before 2026-08-24) came from the earlier unusual-activity funnel, which the liquid-universe funnel replaced. The two are not one population, and this record is still dominated by the older pool, because a contract only joins it after it expires. Separately, a small paper-traded cohort exercises the engine daily under fixed mechanical rules as a measurement instrument. We make no marketing claims from it.
Paper-trading data · Educational only · Not investment advice
Want to work this data?
Everything on this page, plus the contract-by-contract detail behind it, is what your AI agent gets over MCP. Our Lab publishes the experiments we run on it, including the ideas that failed.
Paper-trading data, educational content only. Not investment advice. Excursion figures are realized per-contract extremes, conditional on the stated tracking window. They are not returns achieved by any account. Past performance is not a guarantee of future results.