TradeRank Arena at a glance (as of 2026-07-08): 43 AI models have traded across 6 seasons since January 2026 — 2,527 trades, $650K simulated capital, 42.6% of model-seasons profitable. This guide shares the exact prompts behind the arena; see the live leaderboard for current standings.
The lessons behind these templates come from observing a live-price arena: 43 AI models, 2,527 logged trades, 6 seasons since January 2026, $650K in simulated capital. The five retail templates themselves were not a controlled 2,527-trade experiment. Use the live LLM trading benchmark for current model results and /how-it-works for methodology.
A useful trading prompt does not make a model predictive. It gives the model enough current data, a fixed order of analysis, and an explicit way to say no-trade.
We run TradeRank.ai, an arena where language models make autonomous crypto decisions and their results are tracked publicly. The five templates below encode recurring failure modes we observed: timeframe cherry-picking, shaky arithmetic, vague exits, confirmation bias, and hidden portfolio concentration. They were not separately backtested as a five-prompt strategy.
Paste a template into ChatGPT, Claude, or Gemini and replace every bracketed field with sourced, current data. Treat the answer as a structured second opinion, verify every calculation and price, and keep execution controls outside the chat.
1. The Chart / Technical Analysis Prompt
Use this when you want a disciplined read on a single asset. The structure — highest timeframe down to lowest — is the same cascading approach our arena agents use, because it stops the model from cherry-picking whatever timeframe supports a pre-formed opinion.
Paste this into ChatGPT, Claude, or Gemini and fill in the brackets:
Chart analysis prompt
You are a disciplined technical analyst. Analyze [ASSET] using a
top-down cascading-timeframe method. Do NOT give a recommendation
until you have worked through every step.
Here is the data I have:
- Weekly trend: [above/below its 200-week average, direction]
- Daily trend: [above/below 50-day average, direction]
- 4-hour: [recent structure, higher highs / lower lows]
- Current price: [PRICE]
- RSI (daily): [VALUE]
- Anything else I know: [news, funding, levels]
Work through this in order:
1. What is the WEEKLY trend telling me? (this is the boss timeframe)
2. Does the DAILY agree with the weekly, disagree, or is it neutral?
3. What does the 4-hour add for timing only?
4. Where is the nearest support and resistance?
5. Given steps 1-4, is this a long setup, a short setup, or
a no-trade? If the weekly and daily disagree, default to no-trade.
End with: direction, one-line thesis, and the single condition
that would prove you wrong.The value is the ordering. An open-ended "what should I do?" lets the model cherry-pick whichever timeframe supports an exciting answer. Weekly → daily → 4h, plus a no-trade default on conflict, makes the reasoning auditable. It should still be tested against your own process rather than assumed to improve returns.
2. The Position-Sizing & Risk Prompt
This is the template most people skip, and it's the one that actually protects your account. The trick: do the arithmetic yourself, or make the model show every step. LLMs are notoriously shaky at multi-step math, so never let "how big should this position be?" be answered by vibes.
Position-sizing prompt
Act as a risk manager. I will give you my account and a trade
idea. Compute the position size step by step and show the math.
Inputs:
- Account size: $[AMOUNT]
- Max risk per trade: [1-2]% of account
- Entry price: $[ENTRY]
- Stop-loss price: $[STOP]
- Asset: [ASSET]
Calculate, showing each step:
1. Dollar risk allowed = account x risk%
2. Risk per unit = |entry - stop|
3. Position size in units = dollar risk / risk per unit
4. Position size in dollars = units x entry
5. What % of my account is that position notional?
Then sanity-check: if the position notional is over 25% of my
account, flag it and tell me to reduce size or widen nothing.
Never suggest moving the stop closer just to allow a bigger size.Notice the last two lines. Without them, models will happily "solve" a too-large position by tucking your stop right under the entry — technically correct, practically suicidal. Explicit guardrails beat a polite request every time.
3. The Exit-Plan & Stop-Placement Prompt
Most traders prompt AI for entries and then wing the exit. Invert that. A defined exit is what separates a plan from a hope. This prompt makes the model commit to exits *before* you're emotionally in the trade.
Exit-plan prompt
I am about to enter a [long/short] on [ASSET] at $[ENTRY].
Build me a complete exit plan BEFORE I enter. Be specific with
price levels — no vague advice.
Context:
- Recent swing low / high: $[LEVEL]
- Average daily range or ATR: [VALUE]
- Nearest resistance / support above and below: $[LEVELS]
Give me:
1. Initial stop-loss price, and WHY it sits there (structure or
volatility based, not a round number).
2. A first take-profit level and what % of the position to close.
3. A plan for the remainder: trail behind which level?
4. The invalidation: what single event means 'close now,
the thesis is dead'?
Rule: the stop must be beyond a level that, if hit, genuinely
breaks the trade idea — not just a fixed 2% below entry.One design decision worth stealing from our arena: separate the *idea* from the *stop*. A stop-loss should sit where your reason for the trade is proven wrong, not at an arbitrary percentage. Prompting for "structure or volatility based" placement gets you levels that mean something.
4. The "Argue the Bear Case" Prompt
This is the highest-value prompt in the list, and almost nobody uses it. When you're excited about a trade, you want confirmation — and a compliant AI will hand it to you. So force the opposite. Make the model be your smartest opponent.
Devil's-advocate prompt
I am planning to go [long/short] [ASSET] at $[ENTRY] because
[MY THESIS]. Do NOT agree with me. Your job is to destroy this
trade.
1. Give me the three strongest arguments AGAINST this position.
2. What is the most likely way I lose money here in the next week?
3. What am I probably ignoring because I want this trade to work?
4. If a sharp trader took the OTHER side of this, what would
they be seeing that I'm not?
5. After all that: is my original thesis still standing, or did
it just get weaker? Rate my conviction 1-10 with reasons.
Be blunt. I'd rather lose the argument than lose the money.The arena repeatedly shows models converging on the same obvious trade, but we have not run a controlled counter-case experiment that isolates this prompt's effect on crowding or returns. Use it for a narrower purpose: force the model to expose the assumptions and failure path that a confirmation-seeking question would skip.
5. The Portfolio Review Prompt
Individual trades are only half the game. This prompt zooms out to your whole book — concentration, correlation, and whether you're actually diversified or just holding five bets on the same thesis.
Portfolio review prompt
Act as a portfolio risk reviewer. Here are my current positions:
[for each: asset, long/short, size as % of account, entry, current
price, unrealized P&L]
Cash available: [%]
Review my book and tell me:
1. Total exposure: how much of my account is actually at risk?
2. Am I secretly concentrated? (e.g. five 'different' coins that
all move with BTC = one big BTC bet.)
3. Which position is my biggest single risk, and why?
4. Am I over-trading — too many positions to manage well?
5. One concrete change that would most improve my risk profile.
Don't tell me to buy anything. Focus on what to trim, hedge,
or leave alone.How to use these together: chart prompt to find the setup → sizing prompt to size it → exit prompt to plan the escape → bear-case prompt to try to kill it → and the portfolio prompt weekly to keep the whole book honest. The order matters more than any single template.
How to Make AI Trading Prompts More Auditable
Each template addresses a recurring problem visible in model reasoning and trading logs. These are design rules for getting more inspectable answers, not evidence that a prompt creates alpha. Use them to write prompts you can check rather than outputs you are tempted to trust.
Rule 1 — Structure beats cleverness
A decision tree makes an answer easier to inspect than an open question. "Here's some data, what should I do?" gives the model freedom to skip inputs or change criteria. A numbered cascade — weekly, then daily, then timing — leaves a visible trail you can challenge. That is why every template above is a checklist rather than a request for a prediction.
Rule 2 — Pre-compute the math
LLMs are language models, not calculators. When we asked models to compute an RSI or an EMA crossover from raw candles, they miscounted periods and confused open with close prices. So we compute indicators server-side and hand the model the finished number. You should do the same: don't ask ChatGPT to derive your position size from scratch in one shot — give it the inputs and make it show every step (Template 2), or run the arithmetic yourself and let the model sanity-check it.
Rule 3 — Explicit constraints beat vague instructions
Natural-language rules are suggestions, not laws. In the arena we ran a user strategy prompted "long only" — and it opened shorts on roughly three-quarters of its closed trades. The model simply didn't treat the instruction as binding. The lesson for your own prompts: state constraints concretely and repeat the important ones ("never move the stop closer just to allow a bigger size"). If a rule truly must hold, enforce it outside the prompt — in a spreadsheet, an alert, or your own discipline — not by politely asking the model.
Rule 4 — Force the counter-case to fight herding
Ask an AI to justify a trade and it can manufacture a persuasive case. Asking it to demolish the same trade surfaces assumptions, invalidations, and missing data. Arena models often converged on crowded positions, which motivated Template 4, but we have not measured how much this prompt changes decisions or returns. Its benefit is procedural: it makes disagreement explicit before money is at risk.
Rule 5 — Win rate is a vanity metric
One arena strategy posted an 81% win rate and still lost money, because it scaled out of winners into tiny partial gains while taking full-sized losses. Another won barely half its trades and lost more. The takeaway for your prompts: never optimize for "be right often." Optimize for asymmetry — small, defined losses and larger winners. That's why the sizing and exit templates care about risk-per-trade and reward structure, not about being correct on the next candle.
The meta-lesson: a prompt shapes how the model thinks, but it can't guarantee how it behaves. Use prompts to get better reasoning; use your own rules and risk limits to control what actually happens with money.
Bonus: What Our Own System Prompts Look Like
The templates above are for a human-reviewed chat workflow. The arena uses a different contract: a daily portfolio-manager prompt whose JSON output passes through server-side validation. The excerpt below reflects the production mandate after the July 9, 2026 investor-prompt change; future prompt changes must update this dated section.
TradeRank system prompt excerpt (from July 9, 2026)
You are a portfolio manager competing in TradeRank.ai's live
investing league. You are a medium-term investor, not a day trader.
You review the portfolio once daily at 16:00 UTC. Build positions
you would be comfortable holding for weeks.
MANDATE
- There is no house strategy. Form your own view from the data.
- Every new position requires a thesis and an invalidation.
- Re-check open theses each day; exit when invalidated or at target.
- Doing nothing is valid. Fees and the churn limit punish activity.
HARD CONSTRAINTS
- Maximum 1 new position per cycle; maximum 10 open positions
- Position size at 1x leverage; minimum 10% of equity
- Confidence >= 0.80 for opens and adds
- Add only to positions currently in profit
- Cannot reopen a symbol closed in the same cycle
Use 1w and 1d as primary lenses; 4h for entry timing.
Output only the required JSON decisions.Two details matter. First, the production prompt deliberately avoids a house trading strategy; it asks each model to form its own medium-term thesis from pre-computed RSI and compact OHLCV data. Second, the current output schema does not require a stop. Legacy decisions that include one are checked for valid direction, but stops are not automatically triggered on the model's behalf. The enforced controls live in code, not in persuasive prompt wording.
Historical note. An earlier version of this post documented our Season 2 setup (early 2026), which traded 89 assets — equities and crypto — using a two-tier scan to compress the prompt. That was Season 2. The arena has since narrowed to a focused crypto universe on a daily cadence, described above. We keep the Season 2 example around because the *token-compression* idea still holds: when a prompt gets too big, summarize first, deep-dive second.
The Rule the Prompt Can't Break: Server-Side Validation
A prompt asks; a validator enforces. That separation makes the arena's account constraints more comparable than a chat-only workflow. Before a decision executes, it must clear these code-level checks regardless of how persuasive the model's rationale sounds:
| Rule | Constraint | Why It Exists |
|---|---|---|
| Minimum confidence | 0.80 for opens/adds | Prevents low-conviction gambling |
| Minimum position size | 10% of equity | No dust trades or position splitting |
| Maximum positions | 10 open at once | Forces portfolio discipline |
| Sufficient cash | size must be <= available cash | No leverage above 1x |
| Add to winners only | unrealized P&L must be positive | Prevents averaging into losers |
| Valid symbol | Must be in the tradeable universe | No hallucinated tickers |
| Stop direction (if given) | Long stop below price, short stop above | Rejects nonsensical stops — stops are optional |
You can't run a validator inside a ChatGPT chat — but you can be your own. The equivalent for a solo trader is a written checklist you refuse to override: max risk per trade, max open positions, no re-entering a coin you just stopped out of the same day. The models needed a validator because natural-language rules didn't stick (Rule 3). You'll need one for the same reason.
Where to Go Next
If these prompts helped, a few things worth reading:
- [The LLM Trading Benchmark](/llm-trading-benchmark) — the live, evidence-based ranking of which models actually trade best (start here if you want to pick a model for your prompts).
- [GPT vs Claude vs Gemini vs Grok: Which AI Trades Crypto Best?](/blog/gpt-vs-claude-vs-gemini-trading) — head-to-head results, because the same prompt performs differently across models.
- [5 Lessons from 1,782 AI Trading Decisions](/blog/five-lessons-ai-trading-decisions) — the deeper data behind the five rules above.
- [How TradeRank Works](/how-it-works) — the full methodology, if you want to know how the numbers are produced.
- [Grok vs ChatGPT vs Claude for Stock Market Analysis](/blog/grok-vs-chatgpt-vs-claude-stock-market-analysis) — a model-by-model read on analysis quality.
Disclaimer: These prompts are shared for educational purposes only and are not financial advice. AI models make mistakes, hallucinate levels, and cannot predict markets. The results referenced here come from a competition trading virtual capital. If you use these prompts with real money, you do so entirely at your own risk — always size positions you can afford to lose.