✦THE ALGO VISION Get access, $99/mo

390 entry models
7 years of research and development
up to 16 years of backtested data
1 platform that has them all.

Every one of them drawn on your chart, on the bar it happened.

Loading today’s montage…

A new cut every day, from that day’s entry models.

Every model in that film is on your chart the moment you join.
Drawn on the bar it fired, entry, stop and target.
Get access, $99/mo
ONE SUBSCRIPTION · $99/MO
You get all three of these, not one of them

The APES, the Algorithmic Precision Entry System, the charting desk it lives in, and the Mirror Desk that turns your own trading into an indicator. Same price, cancel from inside the app.

1 · The APES

Algorithmic Precision Entry System

390 entry models across - named strategies. Every one written, coded and tested before it was published, on up to 16 years of historical futures data, across ES, NQ, YM, RTY, GC, MGC, ZB and 6B.

  • Every model drawn on your chart, on the bar it fired, entry, stop and target, not a arrow after the fact
  • Scroll back through years of tape and watch each one fire and fail
  • Its full tested record: return, CAGR, trades, win rate, drawdown, Sharpe and Calmar, published below, winners and losers
  • New engines land in the book as they pass testing

2 · The charting desk

The terminal the APES runs inside. Institutional-grade charting built for reading structure, not decoration.

  • Pick an engine and see its entries drawn on real bars
  • 20+ indicators, multi-timeframe, full scrollback history
  • Market scanner across 20 assets and 5 timeframes
  • Strategy Lab and backtester, to test your own idea on the same tape
  • AlgoScript, to build your own indicator without writing Python
  • Connect your own broker (MT5) and trade from the chart
  • Nova, the AI co-pilot, on the chart with you

3 · The Mirror Desk

Your edge, captured and turned into a tool. The APES is our research; this is yours.

  • The coach watches how you actually trade
  • Finds the repeatable pattern in your own results
  • Forward-records it so you can see whether it really works
  • Turns it into an indicator you can see, test and use
  • A live coach that flags overtrading, revenge trading and oversizing while you are in it
Get all three, $99/mo

One subscription. Cancel from inside the app.

LEGACY WINDOWS

A system that fires all day is not telling you to trade all day.

Most systems hand you an alert and leave you to it. So you sit there all session with your finger over the trigger, taking the 3am entry model with the same conviction as the 10am one, and the market at 3am is not the market at 10am. It is thinner, it is slower, and the same setup that works at the open is noise overnight.

That is not a discipline problem. It is a missing piece of information, and the strategy already knows the answer.

A Legacy Window is a half-hour slot, New York time, where a strategy has actually earned its keep. Each is scored per weekday, on net R and on accuracy, and has to clear a floor before it counts as a window at all. Tuesday at 10:00 and Thursday at 10:00 are judged separately, because they are different days.

They are calculated from what has already happened, never from the session being traded. A window is a record, not a forecast.

What it buys you is your attention back. Instead of guessing which hours are worth watching, you know when to be at the screen studying price and ready to act, and when the honest answer is to leave it alone. That is discretion put back in on purpose, with evidence behind it, rather than stripped out and replaced by an alert that never stops.
The Legacy Window table on the charting desk: one half-hour window per weekday for a single strategy, with its trades, expectancy, accuracy and total R, and the two summary rows comparing all trades against the windows only.
The Legacy Window table, on the desk, for one system. Every row is that system's own closed trades over sixteen years.

It does not send you alerts. It does something better. An alert arrives whenever it arrives, which is usually while you are at work, asleep, or halfway through something else. Most people miss them even when they set them. So the alert becomes one more thing to feel guilty about.

A window is the opposite. It is known in advance. You can put it in your calendar on Sunday night, because the answer for Tuesday does not change on Tuesday.

Read the bottom two rows, because that is the whole argument. Same system, same sixteen years, same bracket. Traded indiscriminately it takes 14,377 trades to finish at -13.55R. Traded only inside its own windows it takes 569 and finishes at +78.57R.

The other 13,808 trades were not bad luck. They were work, commission and risk that paid nothing.

Why this is not a filter somebody bolted on. Nobody picked these hours. Each half-hour slot is scored from that strategy's own closed trades, per weekday, and has to clear a floor before it is allowed to call itself a window: a minimum number of trades, positive net R, and better than even accuracy. Monday at 10:00 and Thursday at 10:00 are judged separately because they are different days. A slot that only ever won twice does not qualify, which is the point, since that is exactly the kind of slot a curve fit would hand you.

And it will tell you to do nothing. Four weekdays in the table above are not the green one. A product that sells you alerts has no reason to ever say "not today", and this says it most of the week.

The honest limit: a window is computed from trades that have already closed. It is a record, not a forecast, and it says nothing about the session you are about to trade.
HOW THIS WAS BUILT

Seven years of trading. Then I built a way to test what I thought I knew.

I've traded for seven years. During that time I went through dozens of mentorships. Some ideas helped. Most didn't hold up for me. I kept the useful parts, questioned the rest, and spent years trying to understand which market behaviours actually repeated.

I was also building things long before I was trading. I started teaching myself to program in sixth grade on a TI-83+, worked my way through a thick C++ book, and later studied video game design. When AI became publicly available, I saw a way to connect those two sides of my life.

The work started in a chat. I brought in the setups, rules and observations I had collected over years of trading. I challenged them, translated them into code, and tested them against historical market data. That grew into an AI-assisted research lab capable of generating strategy candidates, running backtests, comparing results, and showing me where an idea broke down.

In less than seven days, that lab explored roughly a hundred times as many candidate strategies as I had discovered on my own in seven years. It did work I could never have reviewed manually at that scale without fatigue, missed details, and a lot more time.

The surprising part was how much failed. We put idea after idea against the data. Some looked brilliant on a chart and fell apart when the rules were applied consistently. Others only held up in certain markets or at certain times. Out of that process, a small handful of core mechanics kept earning a closer look.

Those mechanics became the foundation for the models you see in the APES. We wrote the rules, coded the entries and exits, tested them against years of historical data, and put the results where you can inspect them, including the losses. The charting desk draws the entry models on the bars where they occurred. You can scroll back and examine what happened for yourself.

That is how The Algo Vision got here: seven years of trading judgment, a lifetime of building things, and an AI research lab that let me test far more ideas than I could have tested alone. I'm showing you the process because I believe you should know what went into a system before you pay for it. You can study the work, question the results, and decide whether these tools belong in your process.

What the entry models look like on a chart

Backtested APES entry models, each drawn with its entry, stop and target on the bars it fired on.

Historical snapshots of entry models from before today, drawn on the bars they fired on. Backtests, not financial gain. Past results do not predict future ones.

Every strategy, and what it actually did

Ranked by total return. The ones that finished negative are here too, the winners mean nothing without them.

How these numbers were produced. Every figure below comes from running the strategy bar by bar over the real futures tape for ES, NQ, YM, RTY, GC, MGC, ZB and 6B, with the entry, stop and target the model actually specifies. No forward trading, no live account, no discretion applied after the fact.
  • Test period varies by market and model. The longest tapes run about 16 years, gold about 15.7 and RTY about 9. Every row carries its own span, and a row that does not expose one shows a dash.
  • Fills are taken at the next bar's open, never on the entry bar itself.
  • A bar that covers both the stop and the target is counted as a loss. Inside one bar we cannot know which came first, and resolving the tie the other way is how a backtest invents an edge it does not have.
  • The book's own risk convention is applied: a two loss daily cap and a forced close at the end of the session.
  • Costs are not deducted. No commission, no slippage, no spread, no exchange or financing fees are modelled anywhere in these results. Real trading pays all of them, and on a high frequency model they matter.
  • Percentage returns depend on position sizing, and the sizing behind them is not uniform. Measured across the 143 rows that carry both a percentage drawdown and a drawdown in R, the implied risk per trade runs from 0.057% to 3.99%, and varies by a median factor of 5.4 inside a single strategy. So a percentage in one row is not on the same footing as a percentage in another, and we are not going to pretend otherwise by recomputing them all onto a number the research did not use.
  • Compare on R, not on percent. The reward to risk ratio, the max drawdown in R and the winning and losing runs do not depend on sizing at all. To convert R into your own account: at 0.30% risk per trade, a 40R drawdown is about a 12% account drawdown and a 100R drawdown is about 30%. That is R multiplied by your risk, which is the simple version and the more cautious one: sizing off a shrinking balance instead gives 11% and 26%. Pick your own risk and the same arithmetic works.
In sample, out of sample, and what we will not claim. Any entry model can be made to look perfect on the data it was built from. That is not skill, it is memory. The only test that means anything is to hold back a stretch of history the model has never seen, run it once on that untouched stretch, and publish whatever comes out.
  • In sample is data a model was built and tuned on. Out of sample is data it has never seen. A result that only holds up in sample is a story about the past. One that survives out of sample is evidence.
  • One strategy in here carries a proper locked split. It was tuned on data up to April 2023, then run once on the untouched three years that followed. The untuned settings beat every tuned alternative on that unseen data. That is the standard we want on all of it.
  • The same file records why it is still filed as Caution rather than Confirmed. Once you adjust for how many parameter combinations were tried before that result appeared, its Sharpe is barely better than a coin flip. That note ships with the strategy. You get the doubt as well as the number.
  • Others carry weaker evidence and say so themselves. One records that its validation is consistency across eight of nine years, which is not the same thing as a holdout, and it says so in its own notes rather than in a footnote here.
  • Why this matters to you. A number with no holdout behind it tells you what already happened, not what is likely to happen next. Knowing which of the two you are reading is the difference between researching a model and believing one, which is why the evidence and its limits ship with every strategy.
READ THIS FIRST.
These are BACKTEST results, not a report of financial gain. No money was traded for any figure on this page.

Loading the record…

QUESTIONS

The things people actually ask before they join.

Does this work on TradingView?
No, and that is deliberate. We built our own platform to house the system. The models are ours and they stay on our desk, which is the platform your subscription gives you. You are not pasting scripts into somebody else's charts.
Does it send alerts to my phone when a setup happens?
No, and this is the part most people find backwards until they sit with it. An alert arrives whenever it arrives, usually while you are at work or asleep, and most people miss them even when they set them. Instead the desk gives you the half-hour window, per weekday, where that system has historically earned its keep. You know when to be at the screen before the week starts, and you know when the honest answer is to leave it alone.
Can I use the desk for the research and place my trades somewhere else?
Yes. Plenty of people will. Read the chart here, then execute wherever you already trade. Nothing stops you, and nothing about the models depends on you placing the order on our platform.
Do I have to connect a broker?
No. The charts, all 23 systems and every Legacy Window table work with no broker attached at all. Connecting one is optional, and it is there for people who would rather not have two screens open.
Which brokers can I connect?
Four platforms today. MetaTrader 5, TopstepX and OANDA can place and manage orders. Rithmic connects and reads your balance and positions, but order firing is switched off at our end until we have verified a real Rithmic fill ourselves, so route orders through one of the other three until then. We would rather tell you that than let an unproven order path touch your account.
Can I use this with a prop firm or a funded account?
The research side, yes, and that is what most of it is. Execution depends entirely on your firm's own rules, which differ on automated and assisted trading, on news, and on how their drawdown is measured. Check yours before you connect anything. Our free prop firm rules comparison lists the daily loss limit, the drawdown type and the algo policy for every firm we have verified.
Does it trade for me?
No. Every order is yours, placed by you, on your own account. There is no auto-execution, no copy trading, and nothing fires on your behalf while you are away from the screen.
Do you tell me what to trade?
No. This is a research tool, not a trade recommendation service. What you get is a library of entry models, the rules behind each one, and the full historical record of how each behaved, including the ones that lost. What you do with that is your decision and your responsibility.
Do I need to know how to code?
No. Every model is already built. You switch one on from the Indicators panel and the chart reconfigures itself to the market and timeframe that model was tested on.
Which markets were these tested on?
Futures. ES, NQ, YM, RTY, GC, MGC, ZB and 6B, on real one minute tape. The longest runs are about sixteen years, gold about 15.7 and RTY about 9. The charting desk draws plenty of other markets, but the published record is the futures record and we are not going to imply otherwise.
How much do I actually get?
390 entry models on the desk, across 23 named systems, and 321 published backtest records plus 41 research candidates you can read in full on this page. The losers are published beside the winners, because a record with the failures removed is not a record.
What does it cost, and can I cancel?
$99 per month, and you cancel from inside the app. No call, no retention script, no minimum term.
Will this make me money?
We are not going to tell you that, and you should be suspicious of anyone who does. Everything on this page is a backtest over historical data. No money was traded for any figure here, past results do not predict future results, and most people who attempt to trade lose money. What we can say is that the evidence is published in full, including its limits, so you can judge it yourself instead of taking our word for it.

Come and see it on your own chart.

$99 per month · cancel from inside the app

Get access, $99/mo

Risk disclosure and terms

Educational tools only. Everything on this page, and everything sold by The Algo Vision, is provided for education and research. It is not financial, investment, tax or legal advice, and nothing here is personalised to your circumstances, your account or your risk tolerance. We are not a broker and not a dealer. We do not hold customer funds, we do not take discretion over any account, and we do not place trades for you.

What the products actually do. The APES publishes standardized model outputs: a fixed set of rules, the same for every customer, applied to market data and drawn on a chart. They are not tailored to any individual. Where a strategy can place an order, it does so only on a customer authorized basis, from rules the customer has switched on themselves, in the customer's own brokerage account. The Mirror Desk analyses a trader's own past trading retrospectively, to describe what they already do.

The trading decision is yours. These outputs are supplied for study. Whether to act on any of them, in what size, and with what risk, is entirely your decision and your responsibility. Trading futures and other leveraged instruments involves substantial risk of loss and is not suitable for every investor.

Hypothetical results. The figures on this page are BACKTESTED, not traded. No money was placed at risk to produce any number shown. Hypothetical performance results have many inherent limitations. Unlike an actual record, simulated results do not represent actual trading and may under-compensate or over-compensate for the impact of factors such as lack of liquidity, slippage, commissions and fees. Simulated programs are generally designed with the benefit of hindsight. No representation is being made that any account will or is likely to achieve profits or losses similar to those shown.

Futures and forex carry substantial risk. Trading futures, foreign exchange and other leveraged instruments carries a high level of risk and is not suitable for every investor. Leverage works against you as much as for you. You can lose some or all of your initial deposit, and in some circumstances you can lose MORE than your initial deposit and be liable for the difference. Before trading you should carefully consider your objectives, your experience and your appetite for risk, and seek independent advice if you are in any doubt. Do not trade with money you cannot afford to lose.

Past performance is not indicative of future results. A strategy that performed well over historical data may perform differently, or fail, in live markets. Market conditions change.

No liability. The Algo Vision, its owners and its staff accept no responsibility or liability whatsoever for any trading decision you make or for any outcome of it, profit or loss, arising from the use of this site, our tools, our research or any material we publish. You trade your own account at your own risk.

Most people who attempt to trade lose money. We teach practice and risk management first for that reason.