NEWAgent Library: research agents built on real hedge fund strategies → NEWMeet Edge, your AI coach →
Quantitative research lab

Your own AI market analyst

Hedge AI Labs is a quantitative research lab. Work with our agents to build a trading strategy from an idea or from code you already have, test it with out-of-sample discipline and real costs, and turn the survivors into live market scanners. Then run the whole thing in a simulated account before any capital is at risk.

Not another chatbot: every number is computed by running real code on real market data — stocks, options chains, futures — never estimated, never from memory.

Sign up for free today See how it works
Gap fade, relative-volume filter scanneropen, 09:41 ET
gap > 0.8 × ATR(20) and open_vol < 0.7 × avg_vol(20) and price > 10 and adv > 500k
SymbolGapRel volSim order
MU−2.4%0.58Filled 118.62
FANG+1.9%0.51Filled 172.05
SOFI−3.1%0.74Skipped
CRDO+2.6%0.66Working 94.30
Routed to sim account SA-0417 with slippage and commission modeled
Equity$251,940
Today+$1,940
Open positions3
30-day Sharpe1.31
Agent Library · free with every account

Agent Library: hedge fund research, delivered to you

Ready-made AI agents, each built on a strategy real hedge funds run: trend following, global macro, volatility, activism, earnings, IPOs, fund positioning. Subscribe in one tap. Each agent runs on live market data and official filings on its own schedule, and sends you a plain-English report with tables, only when there's something to report.

Congress trades: what politicians bought and sold

WEEKDAYS 7 PM ET

New STOCK Act disclosures from the House and Senate: who traded what, how much, whose account and how late it was disclosed.

Strategy: alternative dataMore →
Subscribe

Big funds: what they bought and sold

WEEKDAYS 6:30 PM ET

About 30 well-known funds, from Berkshire to Bridgewater: Form 4 trades, 13D/13G stakes, ARK's daily trades and new quarterly 13Fs.

Strategy: filings researchMore →
Subscribe

Activist watch: new 13D stakes

WEEKDAYS 7:30 PM ET

Every new Schedule 13D on SEC EDGAR, from any investor: who crossed 5% of a company, the stake, and what they want (board seats, a sale, a proxy fight).

Strategy: event-driven, activism
Subscribe

Hedge fund consensus & crowding

SATURDAYS 10 AM ET · IN 13F SEASON

Across ~30 funds' latest 13Fs: the most widely held stocks, the highest-conviction bets, consensus buys and crowded exits. The "hedge fund hotel" view.

Strategy: positioning & crowding
Subscribe

Trend signals across markets

SUNDAYS 6 PM ET

The trend in 19 markets CTAs follow (indexes, Treasuries, oil, gold, copper, grains, currencies, Bitcoin): 1/3/12-month returns, trend strength and this week's flips.

Strategy: managed futures (CTA)
Subscribe

Macro regime monitor

MONDAYS 7 AM ET

Yields and the curve, real yields, breakevens, credit spreads, copper vs gold and the dollar, read as one growth/inflation regime. Plus the week's key data.

Strategy: global macro
Subscribe

Sector rotation & breadth

FRIDAYS 5 PM ET

Which of the 11 S&P sectors lead and lag over 1 week to 6 months, their trends, and breadth: equal-weight vs cap-weight, small vs large caps.

Strategy: equity long/short, sector rotation
Subscribe

Volatility risk premium: implied vs realized

WEEKDAYS 6:15 PM ET

Are options pricing more movement than the market delivers? Implied vs realized vol for index, sector and mega-cap names, plus the VIX term structure.

Strategy: volatility arbitrage
Subscribe

High IV Rank: stocks & commodities

WEEKDAYS 9:30 AM ET

The liquid stocks, ETFs and commodities whose implied volatility is highest vs its own past year, with IV Percentile, this week's change and earnings flagged.

Strategy: options volatility
Subscribe

Earnings: implied vs actual moves

WEEKDAYS 3:30 PM ET

For large companies reporting tonight or tomorrow morning: the move options are pricing next to how much the stock really moved after its last 8 reports.

Strategy: event-driven, earnings
Subscribe

Upcoming IPOs: the week ahead

MONDAYS 7:30 AM ET

IPOs expected to price this week on the NYSE and Nasdaq: price range, money raised, implied market cap, lock-up and the business. Plus how last week's new listings trade vs their IPO price.

Strategy: event-driven, new issues
Subscribe

IPO lock-up expirations: insider shares unlocking

SUNDAYS 5 PM ET

Recent IPOs whose lock-up ends in the next two weeks: how many insider shares unlock vs the shares sold in the IPO and normal daily volume, and where the stock trades vs its IPO price.

Strategy: event-driven, lock-up expirations
Subscribe
1 · Subscribe in one tapPick the agents you want. Official agents' reports don't use your credit.
2 · Reports come to youIn the app, by email and on Telegram. Quiet days stay quiet: no filler reports.
3 · Dig deeper or make it yoursAsk a follow-up on any report, or copy an agent and change it in plain English. Members can share their own agents too; we review each one before it's listed.
Sign up free and browse the Library Members: open the Library

Every number is computed from live market data and public filings at run time. Research and education only: the agents show evidence and never tell you to buy or sell.

From the Agent Library · free with every account

Follow the money: Congress and the big funds

Two of the Library's agents read the public filings for you and send a plain-English report when something new is disclosed: what members of Congress traded, and what the best-known funds bought and sold.

Sign up free and subscribe Reports arrive in the app, by email and on Telegram. Or just ask: “which funds own NVDA?”

Research and education only, not investment advice.

✦ EDGEAI coach by Hedge AI Labs

Edge, your personal AI market coach

The only AI agent built around you. Edge learns how you trade from the questions you ask in the lab, tests your ideas on real market data, and writes to you only when something actually matters to what you trade.

  • Learns your styleYour tickers, your rules, your open questions. Each note shows what Edge has learned about you, so you can correct it.
  • Tests your ideasEvery number is computed fresh from live and historical data in that run. Never from memory, never made up.
  • Writes only when it mattersNews, earnings or a big move on names you follow, a major economic release, a setup that matches your own rules. At most one note a day, and quiet days stay quiet.
Sign up free and turn on Edge Included with every account. Notes don't use your credit.

Notes arrive in the lab and by email. Tap 👍 or 👎, ask for notes less often, or stop Edge, all with one tap and no login. Research and education only: Edge shows evidence and never tells you to buy or sell.

✦ Edge · your AI market coachYour exit rule, tested on 352 trades
Why now: last week you asked whether scaling out of winners beats your 8% trailing stop.
Swing trades large-cap growthHolds 1–4 weeksBreakout entriesFollows NVDA, AMD, AVGO

I ran both exits on every breakout that matched your entry rules since 2018: 352 trades. Your 8% trailing stop averaged +9.4% per trade. Scaling out in thirds averaged +1.9%. Nearly all of the gap came from the 40 biggest winners, which scaling out cut short.

Growth of $10k, same 352 entries 8% trailing stop Scale out in thirds
🧪 Want me to…
  • Re-run it with a 10% stop
  • Check which names match your breakout rule today
👍 Useful👎 Not for meLess oftenStop Edge

Illustrative example of a note's format. Results are historical tests, not predictions or advice.

For TradingView users

Take your Pine Script one step further.

Built a strategy on TradingView? Get a second opinion before you trade it. Paste your Pine Script and we'll stress-test it on fresh, out-of-sample data, with real trading costs, compared to buy-and-hold — so you know how much of the edge holds up and where it could be stronger.

Paste your Pine Script
strategy("My Setup", overlay=true)
longCondition = ta.crossover(ta.sma(close,10),
                             ta.sma(close,30))
if (longCondition)
    strategy.entry("Long", strategy.long)
// ...paste the whole script — we translate it
Verdict: no edge — +41% vs buy-and-hold +58%, and 60% of profit was one month. The crossover reacts too slowly to cushion drawdowns.

What we do

Three steps, one pipeline. Start at whichever step matches where your idea is.

{ }

Build a strategy

Start from a hunch, a chart pattern, a paper, or a half-finished script. The agent turns it into precise rules: universe, timeframe, entry, exit, sizing. Pine, Python, or plain English in; an unambiguous, runnable strategy out.

≈

Test the strategy

Replicated as written, never tuned. Lookahead-safe, cost-aware, split in-sample and out-of-sample, bootstrap significance, compared to buy and hold. A clear verdict with the numbers and the bugs we found. Negative results published too.

>_

Build a scanner

The rules that passed become a live scanner over the liquid universe of US stocks, ETFs, and futures. Same definition that was tested, so nothing drifts. Hits arrive in the app, by email, by SMS push, or straight into a sim account.

Or just ask an AI quant analyst

You don't need a strategy to start. Ask a question in plain English and get an answer computed from real market data — stocks, options chains, futures, news — with the code, the charts, and the honest caveats. Not remembered, not estimated: actually run.

Volatility “Compare NVDA's realized volatility to the Nasdaq-100's over 3 months, and find the best convexity trade between NVDA and QQQ options.” → relative-vol structure with the actual IV vs realized numbers Event study “Why did this stock move so much recently? Pull the news around its biggest daily moves this quarter and show how similar moves resolved over the next 2 weeks.” → news-tagged moves + a historical base rate Market health “Where are SPY and QQQ vs their 50/200-day averages, how does the current drawdown compare to history, and what's realized vol doing?” → trend, drawdown percentile, vol regime, this week's headlines Earnings “What's the options market pricing for this week's earnings move, and how did the last 8 earnings moves actually resolve?” → implied move vs realized history, labeled as base rates
Worked exampleReal options + price dataComputed, not estimated

NVDA vs Nasdaq-100 volatility — is NVDA's optionality mispriced?

A user asked to compare NVDA's volatility to the Nasdaq-100's and find the best convexity structure between NVDA and QQQ. Realized vol from daily returns; implied vol from live option chains. 3-month window.

NVDA vol / QQQ vol — delivered2.35×realized, 3-month
NVDA vol / QQQ vol — priced1.83×from implied vol
NVDA implied vs realizedbelowoptionality looks cheap
QQQ implied vs realizedaboveoptionality looks rich
The readNVDA's options were priced at 1.83× the Nasdaq-100's vol but NVDA delivered 2.35× — with its implied vol sitting below its own realized. The structure the numbers point to: own the cheap NVDA convexity, finance it with the richer QQQ side.
Honesty in the loopThe analyst flagged an implausible 0.07 correlation between NVDA and QQQ as a bar-alignment error (the two price series were a day apart), fixed the alignment, and re-ran — rather than reporting the wrong number.
Where it stoppedIt presented the mispricing as evidence, then declined to pitch it as a trade. Analysis, never advice.

Every figure here came from executed code on live market data — not the model's memory. Ask your own question →

Analysis is historical evidence about a market or a strategy — never personalized advice or a recommendation to trade. Illustrative example of output format. Start with any question →

Latest evaluation

Every strategy gets the same pipeline. Negative results are published alongside the positive ones.

Forward logSubmitted strategyReplicationNow running as scanner

Opening gap fade with relative-volume filter

Fade gaps larger than 0.8× 20-day ATR when opening volume is under 0.7× average. SPY, QQQ, IWM. Daily bars, Sep 2023 to Sep 2026. Published 3 Sep 2026.

Return, 3y (SPY)+61.2%buy and hold +58.4%
Max drawdown−10.4%buy and hold −17.2%
Sharpe1.28buy and hold 1.19
Win rate63%94 trades
Profit factor1.47net of 1 bp round trip
Beats buy and hold?Marginally on return, clearly on drawdown. 3 of 3 instruments.
StabilityPositive all 3 years. Bootstrap P(net > 0) 96.4%. OOS Sharpe 1.19 vs IS 1.40.
CaveatRoughly 40% of profit came from April to May 2025. Sample is 94 trades in one dominant regime.

Full report includes per-instrument tables, year-by-year results, exit-rule sensitivity, a cost ladder, and a 10-year extension. Read the full report

Do not fund28 Aug

Dual moving-average crossover with RSI sleeve

SPY, QQQ, ES, NQ. Daily. 12 years.

Return vs buy and hold
+94% / +186%
Max drawdown
−27.5% / −31.2%
Sharpe, PF, win rate
0.58, 1.14, 68%

Trails buy and hold in every window tested. The regime filter reacts too slowly to cushion a fast drawdown, and the exit rule can strand a position when the regime flips.

Fund with limits21 Aug

Overnight hold with contango filter

ES, NQ. Daily. 5 years.

Return vs buy and hold
+71% / +64%
Max drawdown
−9.6% / −25.2%
Sharpe, PF, win rate
1.08, 1.38, 58%

Holds across all 5 years. Filter removes 22% of days. Sized for a 2% daily loss cap. Now running in a sim account for 60 days before the verdict is upgraded.

Browse all evaluations

Illustrative only. The evaluations shown are examples of report format and are not results of actual submitted strategies. Not investment advice.

Custom scanners

Any rule you can state precisely, we can run against the live tape. Scanners are built by the same agents that build and test strategies, so a rule that passed testing ships with the same definition that was backtested. No drift between the test and the thing that fires.

# scanner: gap_fade_rvol
universe:   us_equities, adv > 500k, price > 10
timeframe:  1min bars, evaluated 09:31 to 10:30 ET
gap:        abs(open - prev_close) > 0.8 * atr(20)
volume:     open_vol(5min) < 0.7 * avg_open_vol(20)
direction:  fade toward prev_close
exclude:    earnings within 1 day, halted, index ETFs
deliver:    app, sms, sim:SA-0417
sizing:     0.5% risk per hit, stop 0.6 * atr(14)
  • DataConsolidated US equity and futures feed, 1-minute and daily bars, session VWAP, options chains for large caps.
  • Rule typesPrice and volume, technical indicators, gap and range, relative strength, news and analyst catalysts, earnings calendar, options flow.
  • DeliveryIn-app hit list, email digest, SMS push, or straight into a sim account.
  • Audit trailEvery hit stores the bar and values that triggered it. You can replay any day and see exactly why a symbol fired or was skipped.
  • TurnaroundMost scanners are live the next session. Ones needing new data sources take a few days.
Hits from the same scanner, 4 Sep 2026, with what happened by the close
TimeSymbolGapRel volClose vs entry
09:33MU−2.4%0.58+1.6%
09:34FANG+1.9%0.51+0.9%
09:36SOFI−3.1%0.74rel vol over limit
09:41CRDO+2.6%0.66−0.7%
09:52UAL−1.8%0.62+1.1%
10:07ALAB+3.4%0.69+2.2%
10:18HOOD−2.0%0.44−0.4%

Illustrative output. Hit rate and outcomes vary by day and regime; the scanner does not know which hits will work, and neither do we until the sim account has enough of them.

Build a scanner

Sim trading accounts

Live prices, no real money, fills that cost what real fills cost. An account can be directed by a scanner, by a tested strategy running end to end, or by our research agent trading a mandate you set. Every account keeps a full order log, risk limits, and an auditable track record.

Open a sim account

How we test

The same seven steps for every strategy. In order, because each one depends on the last.

Replicate as written
Apply real costs
Split in-sample and out-of-sample
Bootstrap significance
Check by exact timeframe
Compare to buy and hold
Verdict, then sim

No parameter search. No window selection. Negative results published. Strategies that pass go to a sim account before any verdict is upgraded to fund.

Working with the agent

Everything happens in one thread. The agent reads what you give it, asks only what it can't infer, confirms its interpretation, then runs the full pipeline.

H
Describe the idea or paste what you have. Pine, Python, or plain English all work. I'll turn it into exact rules, test it, and build the scanner if it passes.
You
Here's a Pine script. Fades opening gaps on SPY when volume is light. 
//@version=6
strategy("Gap fade", overlay=true)
atrLen  = input.int(20)
gapMult = input.float(0.8)
…
H
Got it. Three things before I run it:
  1. Instruments: SPY only, or SPY, QQQ, IWM?
  2. Bar timeframe: daily, or does the gap need intraday bars to fill?
  3. Should I treat process_orders_on_close as fill-at-close of the signal bar? That's how Pine does it.
You
All three. Daily. Yes. And if it passes, build it as a scanner and route it to my sim account.
H
Running: SPY, QQQ, IWM. Daily. 3- and 10-year windows. 1 bp round trip. Versus buy and hold. No parameters changed. I'll flag anything in the code that doesn't do what it looks like it does. If the verdict is fund or forward log, I'll ship the scanner with the identical rule definition and route hits to SA-0417 at 0.5% risk per hit.
Rules confirmedReplicatedBacktesting 2 of 3BootstrapReportScannerSim routing

Illustrative conversation. Live chat requires a free account.

What we don't do

Optimize parameters, pick windows, or soften a bad result.

Confidentiality

Your code stays private. Publication only with consent, anonymized. Scanners and sim accounts are visible only to you.

Turnaround

Most daily-bar strategies finish in the session. Intraday and options take longer. Scanners are usually live the next session.

Who it's for

Self-directed traders who want an honest answer before risking capital, strategy developers who want independent replication, and investors who want to see how testing is actually done.

Sign up for free today

A free account gets you the agent chat, the Agent Library, Edge (your personal AI market coach), full evaluation reports, your first scanner, and a sim trading account — with $50 of research credit included, no card required. A full backtest runs about $1–2.50 in credit: hours of coding, data work and honest statistics, done in minutes. Scanners watch the market around the clock at no cost — credit is only used when one fires and the AI checks the signal for you.

Create free account

Contact us

Questions about the lab, partnerships, or your account? Send a note and we'll get back to you.

Or email us directly at info@hedgeailabs.com.