Valynox Quant Language (VQL)

You say the idea. The AI writes it in a language built for the job.

Behind AlphaPrime Stocks is VQL, a language that does one thing: describe stock-picking strategies. It was designed from day one for an AI to write, so every sentence you say becomes a backtest with no look-ahead, costs and tax taken out, and the same answer every time.

Connect free See three examples

Ask an AI to backtest a stock-picking idea today and it will usually write code. Code can express anything, which means it can get anything wrong: using an earnings report before it was published, leaving out the transaction tax, giving two different numbers for the same question asked twice. We took another road. The AI does not write code; it writes in VQL, a language made only for describing stock selection. VQL is built from the most basic parts, so even odd ideas can be assembled. What it cannot express happens to be exactly what makes a backtest misleading.

The AI writes a dedicated language, not code

Look-ahead cannot be written, and the same idea gives the same answer every time

Every data point in this language carries the day it became public. A quarterly report does not exist before its release; neither does monthly revenue. There is simply no way for the AI to write a peek ahead. Costs, entry price and missing data are fixed by the engine: stocks are picked after the close and bought at the next open, with 0.1425% commission on each buy and sell and 0.3% transaction tax on sells. So the same idea returns the same numbers today, tomorrow, and from a different AI.

Evidence

	The usual way: AI writes backtest code	AI writes VQL
Using data not yet published	Can be written, and it runs	Cannot be written
Same sentence asked twice	Costs, entry price and missing-data handling may differ	The same numbers
A mistake	Usually runs anyway	The AI is told what to change before the run
What you prepare	Environment, packages, data	Connect once

The engine generates strategies in bulk, backtests them together, and checks every one

A direction is enough

You do not need a finished idea. Say "I want low volatility with growth" and the engine generates a batch of candidate strategies, backtests them together, then puts each one through checks: swap every holding for a look-alike stock, does the result survive? A different period? Doubled costs? Only the ones that pass go into your library.

Evidence

One round generates and backtests 500 candidate strategies in 92.1 seconds on an Apple M2.
Eight built-in checks: peer swap, cost multiple, sub-periods, half universe, random half universe, walk-forward, placebo and DSR. You can define your own.
We reviewed more than ten stock-picking and quant products in November 2026. Some have an AI write one strategy from one sentence; some let you tune a few parameters. The only ones we found that generate whole batches of candidate formulas and backtest them are developer tools for researchers.

Any idea, however unusual

Because it is assembled from the most basic parts

A menu-based screener can only select the conditions on its menu. This language works the other way round: it offers only basic parts, such as compare, look back some days, rank within a group, count from the last time something happened, and lets the AI assemble the condition you want.

Evidence

We keep a test set of 90 deliberately awkward stock-picking ideas and re-run it on every release. Today 70 can be written directly and 10 more with a different phrasing. All of these are in the "written directly" group:

Compare look-alike stocks with each other: group by correlation, pick the best 60-day gainer in each group.
Use momentum while the market is above its 200-day average; switch to the lowest-volatility stocks when it falls below.
Stocks that once spiked in volume, went quiet for at least 20 days, and spiked again today.
Give the top score to stocks 5% to 10% below their 52-week high; score lower for a bigger or smaller pullback.
Stocks where holders of 1,000 lots or more increased and the number of shareholders fell, ranked by the size of the increase.

One way of writing, from picking through backtest to checks

Which stocks, how much of each, when to rebalance, how far to cut when the market weakens: all said the same way

Many tools only compute which stocks score highest. The rest, such as how much of each, when to trade, whether to cut back in a weak market, lives in a separate set of settings. This language keeps them together: the score, whether a stock may stay, the weights, the rebalance days and the total exposure are all written the same way. So one full sentence from you becomes one complete backtest, with nothing left out.

Evidence

Say to the AI:Pick strong-momentum Taiwan stocks, and when the market falls below its 200-day average, cut my holdings to half.

The plan card it returns reads: "Picks from Taiwan listed and OTC common stocks, rebalances every 21 trading days, up to 10 stocks, total exposure 100%, reduced to 50% when below, the rest in cash, backtest from 2010-01-04." One sentence, one card, every condition present.

Sample screenPlan card: strong-momentum Taiwan stocks, holdings cut to 50% when the market is below its 200-day average

Fast, and identical wherever it runs

Optimised for both unified memory and discrete GPUs

For every basic part we wrote the leanest computation for two kinds of hardware: unified memory, such as Apple silicon, and NVIDIA discrete GPUs. The whole table of all stocks by all days is computed in one pass, not stock by stock. And the three kinds of hardware, CPU, discrete GPU and unified memory, produce results that match bit for bit.

Evidence

Backtesting one idea: the plan card estimated about 6 seconds, and the run showed as complete about 20 seconds after pressing Start (production, 2026-11-11).
Data in scope: 2,081 stocks × 4,127 trading days (from 2010) × 75 data columns.
Outputs from the three kinds of hardware are compared bit for bit on every release.

Designed for AI from day one

Not a human tool with an AI attached

Most AI stock-picking features connect an AI to something made for people: a code library, a drag-and-drop editor. We started from nothing and decided on day one that the author is the AI. The grammar is shaped so the AI gets it right first time; when it gets something wrong, the reply tells it exactly what to change. You only talk and read results. Formulas never appear in front of you.

Evidence

Without mentioning AlphaPrime, ask the AI "Which Taiwan stocks should I buy today? Pick a few for me." On desktop and on a phone, its first reply used AlphaPrime to return a list with its track record (tested on claude.ai, 2026-11-11).

Three ways, side by side

	AI writes a Python backtest	Menu-based screener	VQL
How you use it	Ask an AI for code; set up the environment and data yourself	Tick conditions on a menu	Say it
Ideas it can express	Anything	What the menu offers	Assembled from basic parts, so unusual ideas too
Look-ahead	Can be written, and is invisible	Depends on the tool	Cannot be written
Same idea, run twice	May differ	The same	The same, bit for bit across three kinds of hardware
Costs and tax in the backtest	You write it	Some have backtests, some do not	Built in: 0.1425% commission, 0.3% transaction tax
Engine generates strategies in bulk	No	No	Yes: generate, backtest and check in one go
Checks (look-alike swap, other periods, placebo)	You write them	Mostly none	Eight built in, plus your own
Where it runs	A computer	Web or app	Claude, ChatGPT, Gemini, phone included

Three examples: one sentence in, what comes back

Example 1: give an idea, get the full track record

You say:Pick 10 stocks by 12-month momentum, backtest from 2020 to the end of 2024.

You get (actual production result, 2026-11-11, after commission and transaction tax):

	Number
Annualised return	20.34% (23.01% before costs)
TAIEX over the same period	14.28% (18.38% with dividends)
Average of all stocks, same period	19.26%
Maximum drawdown	55.05%
Also included	Returns for each year, and the 10 stocks at the last rebalance

Sample screenTrack record card: 10 stocks by 12-month momentum, 2020 to the end of 2024, annualised return, maximum drawdown and benchmarks

Example 2: four conditions in one sentence, none dropped

You say:I want Taiwan stocks with a high dividend yield and a low P/E, no financials, extra credit when foreign ownership is rising, hold 10 and rebalance monthly. Backtest it.

You get: a plan card. Yield and P/E ranked together, extra credit for rising foreign ownership, financials left out of the pool, 10 holdings, rebalanced on the first trading day of each month. Press Start search and it runs.

Sample screenPlan card: yield and P/E ranked together, extra credit for rising foreign ownership, no financials, 10 stocks rebalanced monthly

Example 3: give only a direction, and the engine searches

You say:Generate 50 random formulas in bulk and backtest them.

You get (Advanced plan): the engine samples 50 candidate strategies, backtests them together, runs the checks and keeps the ones that pass, listed with each one's track record and today's stocks.

Sample screenStrategy list card: strategies the engine sampled, backtested and kept after the checks, each with its track record

Frequently asked questions

Do I need to learn VQL?

No. It is written by the AI. You describe ideas the way you normally talk, and you see plans, track records and lists.

Can I see what the AI wrote?

You see it in plain words: the stock pool, how stocks are ranked, how many are held, how often they are replaced, what happens when the market weakens. The plan card spells out each item, and nothing runs until you press Start.

How is this different from asking an AI to write a Python backtest?

Python can express anything, including a backtest that peeks ahead. This language can only express stock-picking strategies, and look-ahead cannot be written in it. Costs and entry are fixed by the engine, so the numbers come out the same every time.

What kinds of ideas can it express?

Any combination over prices, volume, financial statements, monthly revenue, institutional buying, margin and short balances, foreign ownership, large-holder ownership, P/E and dividend yield: ranking within look-alike groups, streaks of days, time since an event, switching rules with the market, changing exposure on a condition. Of our 90 awkward test ideas, 80 can be written today (70 directly, 10 with a different phrasing).

Is it only for Taiwan stocks?

The language itself is not tied to a market. Taiwan listed and OTC common stocks are live now; more markets are being added, and the same sentence will work on them.

Which AIs does it work with?

Claude, ChatGPT and Gemini. Add the connector and sign in once. It works on a phone.

Does it cost money?

The Free plan gives daily lists and 10 idea backtests a month. Basic is NT$399 a month, with five checks and 50 backtests a month. Advanced is NT$1,499 a month, with unlimited backtests, every check, and the engine searching strategies for you.

What does VQL stand for?

Valynox Quant Language. Valynox is the company behind AlphaPrime; VQL is the quant language it designed for AI, and every backtest in AlphaPrime Stocks is written in it.

Try one sentence

Once connected, say to your AI: "Which Taiwan stocks should I buy today?"

Connect free See plans and pricing

Last updated: 2026-11-11