AI backtesting agent for CME futures It writes the strategy.
Then it tries to break it.

Describe an idea in plain English, or draw it on a chart. The agent writes it in Python, backtests it on CME futures data since 2010 and runs the checks most results fail.

No card needed. Free credits every month.

How the AI agent builds and backtests a strategy

Reads your chart

Draw your levels and boxes as you always have. The agent reads them as prices, writes the rules they imply and draws its trades back.

Exported to your platform

Pine Script compiled from the tested file, and a port for NinjaTrader or any other platform on request.

Finds where it works

Results split by the morning's range, trend, session and news days, and the one filter the numbers argue for.

Shows every step

Every study, file and run is a row in the chat, with what it read and how long it took. Nothing happens off the record.

A demonstration on a simulated ES market, not a result.

Anti-overfitting protocol Validated the way
quant funds do it.

Every winner goes through the protocol institutional quants use, in order, with the last two years of data locked until the final test. A result that only fits its own data does not get through.

Validation report

ES opening range breakout

52 trials, 2016 to 2025

Verdict 6 of 6 passed Robust

Fit 2 years, trade 6 months, 12 times

Stop 32, target 56 chosen in 9 of 12

Sharpe fitted
2.06
Sharpe traded
1.70

A demonstration on simulated data: the research log's 52 trials over ten years of a simulated ES market, 2016 to 2025, through the protocol.

Robustness checks

Then six checks
try to break it.

Each one kills a kind of result that only looked good.

  • Parameter stability

    Every setting one step either way. A peak with cliffs around it is noise that landed well.

  • Cost breakeven

    Slippage, fees and latency raised until the edge is gone. You learn the cost it survives.

  • Random-entry test

    The same stops, targets and hours, with entries at random. If chance does as well, the signal adds nothing.

  • Other markets and timeframes

    The same rule, unchanged, on another contract and other bar sizes. An edge in one place only is where the data was cut.

  • Lookahead and repainting

    The code is read for both before a run is spent. No decision may see a bar that had not closed.

  • Best days removed

    The ten best days taken out. An edge that lives in a handful of days was a handful of lucky days.

Research log It remembers
every attempt.

Every idea, why it was tried, what measured it and what became of it, the failed ones too. It never runs a test twice, and every attempt counts against the winner.

A log of every idea

What was tried and why, what measured it and what became of it. Ask about any line and the agent opens the runs behind it.

Every attempt counted

Four ideas and a sweep of 48. The winner's Sharpe is deflated for all 52, the dropped ones too.

Every change, a version

The diff of what was kept, and the runs that measured both sides of it.

Features

Prop firm challenges Tuned to the
firm's rules.

It runs every version through the challenge ten thousand times, reads how the attempts end, and changes the strategy and its size until the odds hold.

94% Kept

of 10,000 attempts at a Topstep 50K Trading Combine pass, in 21 trading days at the median.

Atlantive agent

Skipping narrow mornings lifts it to 94%, passing in 21 trading days at the median. Failures fall from 28% to 6%.

A demonstration: the page's strategy on a simulated ES market, through the product's prop engine. On 28 trades the engine's interval for version 2 runs from 21% to 100%.

Models and budget Your model.
Your budget.

Choose any frontier model for each chat, set how hard it thinks, and cap what a month can spend.

  • Every frontier model

    Claude, GPT, Gemini, Grok, DeepSeek and the rest, chosen for each chat, with how hard it thinks.

  • A budget that holds

    Free credits every month, $10 for now, under a cap you set. One answer can only spend a share of what is left.

  • Research, never orders

    It never places an order or touches a brokerage account. It measures, you decide.

Atlantive vs ChatGPT and Claude The same models,
on real market data.

A chat app can write a strategy. It has no futures data to test it on, and it can quote a number no run produced. The agent gives the model you already use the market, the engine and the method.

ChatGPT or Claude on its own compared with the Atlantive agent
ChatGPT or Claude On its ownAtlantive agent The same models, free to start
Writing it
The codeIn any language you ask forA short Python file in your workspace
Your chartReads a screenshot of itReads your drawings as prices and turns them into rules
TradingViewWrites the Pine from scratchCompiles the tested file to Pine Script
Testing it
Market dataOnly what you paste or uploadCME futures, one-second bars since 2010
The backtestIn a general Python sandbox, when it has oneA futures engine: next-bar fills, fees and each market's slippage
The numbersIt can state a figure no run producedOnly from runs, each linked to its run
Trusting it
OverfittingYours to ask aboutWalk-forward, purged cross-validation, deflated Sharpe
Out-of-sample daysYours to keep apartHeld out, run once, logged as seen
Failed ideasForgotten by the next chatLogged, never retried, counted against the winner
Prop firm rulesNot built inPass odds from the strategy's own trades

Writing it

The code
ChatGPT or Claude:In any language you ask for
Atlantive agent:A short Python file in your workspace
Your chart
ChatGPT or Claude:Reads a screenshot of it
Atlantive agent:Reads your drawings as prices and turns them into rules
TradingView
ChatGPT or Claude:Writes the Pine from scratch
Atlantive agent:Compiles the tested file to Pine Script

Testing it

Market data
ChatGPT or Claude:Only what you paste or upload
Atlantive agent:CME futures, one-second bars since 2010
The backtest
ChatGPT or Claude:In a general Python sandbox, when it has one
Atlantive agent:A futures engine: next-bar fills, fees and each market's slippage
The numbers
ChatGPT or Claude:It can state a figure no run produced
Atlantive agent:Only from runs, each linked to its run

Trusting it

Overfitting
ChatGPT or Claude:Yours to ask about
Atlantive agent:Walk-forward, purged cross-validation, deflated Sharpe
Out-of-sample days
ChatGPT or Claude:Yours to keep apart
Atlantive agent:Held out, run once, logged as seen
Failed ideas
ChatGPT or Claude:Forgotten by the next chat
Atlantive agent:Logged, never retried, counted against the winner
Prop firm rules
ChatGPT or Claude:Not built in
Atlantive agent:Pass odds from the strategy's own trades

What else the agent does

Questions about the AI agent.

What is the Atlantive agent?

The Atlantive agent is an AI backtesting agent for CME futures. It turns a trading idea written in plain English, or drawn on a chart, into a short Python strategy, backtests it on historical futures data and reports what it measured: the trades, the equity curve, the drawdown and whether the result holds up. Along the way it studies the market, reads the research, keeps a log of every attempt and plays a finished run through a prop firm's rules.

How is the Atlantive agent different from asking ChatGPT or Claude?

The Atlantive agent runs on the same kind of models, Claude, GPT and Gemini among them, and gives them a futures market and an engine. A chat app has only the data you paste and can write a figure no run produced. The Atlantive agent backtests on CME futures data, quotes only numbers its runs returned, keeps every version of the file, and checks a winner before it calls it one.

Do I need to know how to code to use the Atlantive agent?

No. You describe the idea in your own words and the Atlantive agent writes the code. What it writes is an ordinary, short Python file that you can open, read, edit and run again, so nothing about how the strategy trades is hidden from you, and a trader who codes can change the file by hand.

Can the Atlantive agent turn discretionary trading into rules?

Yes. Draw your levels, zones and trendlines on the chart as you always do, and tell the Atlantive agent what you do there. It reads each drawing as prices and times, writes the rules it implies as a strategy, backtests them, and draws its own trades back on your chart, so you see where the rules agree with your eye and where they do not.

Can the Atlantive agent show where a strategy works and where it loses?

Yes. The Atlantive agent splits a backtest, or a trade list you bring, by regime: trending or ranging days, high or low volatility, the session, and days with economic releases or news. It shows where the strategy makes and loses money, proposes the filter the numbers argue for, and runs the filtered version once on days it never saw before calling it better.

Which market data does the Atlantive agent backtest on?

The Atlantive agent backtests on futures traded on CME Globex: equity index, rates, currencies, energy, metals, agriculture and crypto, such as ES, NQ, ZN, 6E, CL, GC and BTC. Strategies run on price bars from one second to one month, with history back to 2010, and every market fill pays a commission per contract and a tick of slippage. The backtesting engine page has the details.

How does the Atlantive agent avoid overfitting a backtest?

The Atlantive agent puts every winner through the anti-overfitting protocol quant funds use. The last years of data are locked before the first look; the rest goes through walk-forward analysis, combinatorial purged cross-validation and the probability of backtest overfitting; the Sharpe ratio is deflated for every attempt, failed ones included; a Monte Carlo sets the drawdown to expect; and the locked years are opened once. Six checks then attack the edge itself, from costs to random entries.

How does Atlantive prevent lookahead bias?

In Atlantive a strategy decides at a bar's close and its order fills at the next one-second bar, never on the bar it decided on, so no decision sees data it could not have had. Strategies are written in a closed trading vocabulary that is checked before they run, and every run records what examined its days before it, so a held-out period already looked at is never reported as unseen.

Which AI models can the Atlantive agent use?

The Atlantive agent runs on the model you choose for each chat: Claude, GPT, Gemini, Grok, DeepSeek, Qwen and other frontier models, with how hard it thinks set per chat. The model writes and reasons, and the numbers always come from Atlantive's engine, so a cheaper model changes how well the agent works through an idea, not how a backtest is measured.

How much does the Atlantive agent cost?

Signing up for Atlantive is free and open to everyone, with no card asked for, and for now every account receives $10 of agent credits each month. A credit is a dollar of model use at the provider's price, and one answer may spend only a share of what is left, so a single question cannot use up the month. Backtests and prop simulations spend no credits.

Are my strategies private on Atlantive?

Yes. Your strategies, code, files, backtests and conversations in Atlantive remain yours, and Atlantive does not sell them or use them to train models. The Privacy policy names the providers that process them to produce the agent's answers.

Can the Atlantive agent test a strategy against a prop firm challenge?

Yes. The Atlantive agent plays a finished backtest through a prop firm's challenge rules, such as a 50K Topstep Combine, or rules you set yourself. The prop firm simulator resamples the run's own trades into thousands of attempts and reports the chance of passing each phase, the days it takes and the chance of blowing the account, and the agent then fits the contracts and the daily stop to the rules.

Can I take an Atlantive strategy to TradingView or NinjaTrader?

Yes. A strategy the Atlantive agent writes compiles to Pine Script, TradingView's language, with one click. The TradingView export translates the file that was tested rather than asking a model to write Pine again, and it refuses, by name, anything a chart cannot reproduce. For NinjaTrader, TradeStation or another platform, ask the agent to port the rules to its language: a port is a translation, so test it there again.

Can the Atlantive agent trade for me?

No. The Atlantive agent researches strategies and never places orders or connects to a brokerage account. What it reports are measurements of how rules would have behaved on past prices, not forecasts or recommendations, and nothing it says is investment advice. Trading futures carries a risk of loss, as the Risk disclosure explains.

May we measure this visit?

With your consent, Google Analytics and PostHog count visits to these pages. You can separately allow Google Ads to measure visits from our ads. Visit measurement starts only after you choose. Cookie policy