AI Trading Prompts: 5 Copy-Paste Templates for ChatGPT and Claude

Five ready-to-use prompts for ChatGPT, Claude, and Gemini — plus prompt-design rules built from failure modes observed in a live AI trading arena.

Data Point

TradeRank Arena at a glance (as of 2026-09-12): 56 AI models have traded across 9 seasons since January 2026 — 2,826 trades, $910K simulated capital, 46.2% of model-seasons profitable. The arena exposed the failure modes behind these templates, but the five retail prompts were not tested as a controlled treatment across those trades. See the live AI trading competition for current standings and how the arena 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 and US-equity 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

Position sizing turns a trade idea into a defined account risk. Do the arithmetic yourself, then use the model to show the same calculation step by step as a check. Never accept a position size that arrives without the entry, invalidation level, risk per unit, and account-risk cap that produced it.

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 reduce the size or reject the trade.
Never move the stop closer merely to permit a larger position.

The last two lines keep two separate decisions separate. The invalidation level comes from the trade thesis; the position size comes from the distance to that level and the account-risk cap. Moving the stop only to make the size fit changes the trade rather than solving the sizing problem.

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

Use this before acting on a trade you already want to take. A prompt that asks only for support can produce a polished version of your existing view. This one forces the model to state the opposing case, the likeliest failure path, and the evidence your thesis may be ignoring.

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.
Key Insight

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 audit the whole book. The order matters more than any single template.

How to Make AI Trading Prompts More Auditable

Make an AI trading prompt auditable by forcing it into a fixed shape: give the model a numbered decision order instead of an open question, hand it pre-computed indicators rather than raw candles, state each constraint explicitly, and make it argue the counter-case. Each move leaves a reasoning trail you can challenge. None of it manufactures alpha; it just makes the model's thinking inspectable.

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

The arena computes indicators server-side so every entrant receives values produced by the same deterministic code. Asking each model to reconstruct RSI or an EMA crossover from raw candles would add an avoidable calculation step and make the inputs less comparable. For your own workflow, give the model the finished inputs and make it show the position-size arithmetic (Template 2), or run the calculation yourself and use the model only as a check.

Rule 3 — Explicit constraints beat vague instructions

Natural-language rules are suggestions, not laws. In Season 2, the RamonCapital user strategy said "long only" in its prompt but still opened 2 shorts among 17 opening actions. That is not most of its trades, but it is enough to show the instruction was not a hard control. State constraints concretely, and if a rule truly must hold, enforce it outside the prompt — in validation code, a spreadsheet, an alert, or your own execution checklist.

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

TheTradingFox finished Season 2 at -0.35% despite an 81.3% win rate: its average winning close was $2.27 and its average loss $20.91. WolfOfClaude won 52.1% and finished at -3.30%. The examples do not identify an ideal win rate; they show why a hit rate without win and loss size is incomplete. That is why the sizing and exit templates focus on account risk and invalidation rather than the chance of being right on the next candle.

Key Insight

The lesson underneath all five: 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 abridged excerpt below reflects the production mandate and invalidation regime as reviewed on August 27, 2026.

TradeRank system prompt excerpt (reviewed August 27, 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
- invalidation_price is required on open/add and must be on the
  losing side of entry; touching it triggers an automatic close
  between daily reviews

Use 1w and 1d as primary lenses; 4h for entry timing.
Output only the required JSON decisions.

The production prompt deliberately avoids a house trading strategy; it asks each model to form its own medium-term thesis from pre-computed indicators and compact OHLCV data. Every open or add must now include an `invalidation_price` on the losing side of the current price. The validator rejects a missing or wrongly sided level, and a separate monitor checks open positions every 15 minutes and closes one when price touches its level (crypto around the clock; equities during the NYSE regular session). Positions opened before this regime have no enforced level until the model arms one in a hold decision.

Data Point

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 now runs a focused universe of crypto and large-cap US equities on a daily schedule, described in the banner 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:

RuleConstraintWhy It Exists
Minimum confidence0.80 for opens/addsPrevents low-conviction gambling
Minimum position size10% of equityNo dust trades or position splitting
Maximum positions10 open at onceForces portfolio discipline
Sufficient cashsize must be <= available cashNo leverage above 1x
Add to winners onlyunrealized P&L must be positivePrevents averaging into losers
Valid symbolMust be in the tradeable universeNo hallucinated tickers
Required invalidationOpen/add must supply a losing-side priceRejects missing or wrongly sided levels; a 15-minute monitor enforces accepted levels

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.

Adapting the Templates: Trading Bots, Day Trading, and Strategy Design

The five templates assume a human pasting data into a chat. Three variations come up often, and each needs a different adaptation.

As a system prompt for a trading bot. A prompt for a trading bot is a contract, not a conversation: it runs unsupervised, so it needs a fixed output format (JSON, not prose), explicitly stated constraints, and validation code that rejects anything malformed. The "What Our Own System Prompts Look Like" section above is exactly this pattern — a mandate, hard constraints, a required JSON schema, and a server-side validator enforcing what the prompt can only request. If you're building a bot, start from that excerpt rather than the chat templates: keep the timeframe cascade and the no-trade default, but move every rule you actually care about out of the prompt and into code.

For day trading. Our arena makes one decision per day at 16:00 UTC, so nothing in our data validates intraday behavior. The mechanical changes are straightforward — swap the weekly/daily/4-hour cascade for something like 4-hour/1-hour/5-minute, feed intraday ATR instead of daily, tighten invalidations to the session. What we cannot vouch for is whether any of it helps at that speed: fees, spread, and slow LLM round-trips weigh far heavier intraday, and none of our results cover it. Treat day-trading prompts as untested territory, not a faster version of what we've measured.

For strategy design. A prompt for a trading strategy is a different job from a trade-decision prompt. Instead of "analyze this chart," ask the model to draft rules you can test: an entry condition, an exit condition, a sizing rule, and the market regime the strategy should fail in. Then backtest the rules. Don't grade a strategy on how convincing the prose sounds.

Agentic Trading Prompts: When the Model Acts Instead of Answers

The five templates above are single-shot: you paste data, the model answers, you decide. An agentic trading prompt closes that loop — the model holds standing authority to read market data, decide, and place the order on a schedule, with no human between decision and execution.

That changes what the prompt must contain. A chat prompt can rely on you to sanity-check the output before acting; an agentic prompt cannot, so the constraints move from advice to law: a structured output format the executing code can parse, hard risk limits — position count, sizing caps, an invalidation level on every position — and server-side validation that rejects a rule-breaking decision instead of trusting the model to follow instructions. Our arena agents run exactly this way daily; the system-prompt excerpt above and the validation table below show both halves, and How We Built an AI Trading Arena walks the full pipeline.

If you are building one, start from the position-sizing and exit-plan templates — standing rules translate to code most directly — and wire the bear-case prompt in as a pre-trade gate the loop must pass before any order goes out.

Where to Go Next

If these prompts helped, a few things worth reading:

Warning

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.

Frequently Asked Questions

What's a good ChatGPT prompt for trading?

A good trading prompt gives the model a structure to follow instead of asking it to freestyle. Here's a compact one you can paste in: "Act as a disciplined analyst. For [ASSET], work top-down: (1) weekly trend, (2) does the daily agree, (3) 4-hour timing, (4) nearest support/resistance, (5) verdict — long, short, or no-trade, defaulting to no-trade if weekly and daily disagree. End with a one-line thesis and the single event that would prove you wrong." The forced ordering and the no-trade default are what make it useful — they stop the model from cherry-picking whatever timeframe supports an exciting call.

How do I prompt AI to analyze a stock or crypto chart?

Two things matter. First, give the model sourced numbers rather than expecting it to recover exact values from a chart image — feed it the trend on each timeframe, current price, RSI, and key support/resistance levels as text. Pre-computing those inputs reduces arithmetic and transcription work inside the answer. Second, make it reason in a fixed order (weekly → daily → 4-hour → levels → verdict) and ask it to name one condition that would invalidate the read. The chart-analysis template in this article is built exactly this way.

Can ChatGPT actually trade profitably?

The TradeRank record does not establish reliable profitability. Across 56 distinct competitors, nine completed seasons, and 2,826 trades, only 42 of 91 model-seasons (46.2%) finished profitable. These are simulated accounts on live prices, and the result is not a controlled test of ChatGPT alone or of the five templates on this page. Use the prompts to structure and challenge an analysis, not as evidence that a model can produce a durable trading edge.

Do trading prompts work the same across ChatGPT, Claude, and Gemini?

The structure transfers, but the answers can differ. In our arena, entrants share the same mandate, constraints, and whole-universe feature table, yet they still choose different trades. Their full context is not identical once portfolios diverge: each model also receives its own positions, prior thesis state, and deeper candle data for relevant symbols. Test the same retail template across two or three models, verify every claim against the supplied data, and prefer the answer you can audit rather than the most confident one. Our LLM trading benchmark tracks how the models compare on live results.

What is a good Claude prompt for stock analysis?

Give Claude current sourced data and a fixed output contract: summarize the business and catalyst, list the strongest bull and bear cases, identify missing information, state one falsifiable thesis, and name the event that invalidates it. Ask for citations to the supplied filing or earnings text. Do not ask Claude to invent current prices, calculate indicators from memory, or place the trade for you.

Were these five prompts tested across all 2,826 arena trades?

No. The 2,826 trades are the arena corpus that exposed recurring failure modes such as overtrading, vague exits, and convergent reasoning. The five copy-paste templates were designed around those observations, but they were not run as a controlled treatment across the corpus. They should be evaluated as workflow templates, not as a backtested strategy.

What's a good AI prompt for a trading bot?

A trading-bot prompt needs three things a chat prompt doesn't: a strict output schema (JSON, not prose), constraints stated as rules rather than suggestions, and external validation code that rejects anything malformed — models do not reliably obey natural-language rules. Our arena's own system prompt, excerpted in this article, follows that pattern: mandate, hard constraints, required JSON output, and a server-side validator enforcing what the prompt can only request. Keep every rule you actually care about in code, not in the prompt.

Do these AI trading prompts work for day trading?

We can't say — our arena makes one decision per day, so none of our data covers intraday trading. The structural ideas transfer (a timeframe cascade, pre-computed numbers, a no-trade default), and you would swap the weekly/daily/4-hour cascade for intraday timeframes. But fees, spread, and slow LLM round-trips weigh much heavier at that speed, and we have not validated any of it. Treat day trading as untested territory for these templates.

Do these prompts work with Qwen, DeepSeek, or Grok?

You can use the same template structure with other general-purpose models, including Qwen3.8 2.4T A95B, DeepSeek V4 Pro 0813, and Grok 4.6. That is compatibility, not evidence that the prompt improves returns. Supply the same sourced inputs, require the same output fields, and compare whether each answer follows the requested steps and survives fact-checking.

Can I use these AI prompts for forex trading?

The structure can be adapted, but we have not tested it on forex. You would need current pair-specific data, suitable timeframes, spread and rollover costs, and risk rules that account for leverage. The evidence behind this guide is narrower: our arena runs crypto and US equities only, so it cannot support a claim that these templates work in forex.

Can I use these AI prompts for options trading?

Partly. The prompt structure carries over for the underlying: the timeframe cascade gives you direction and the exit-plan template gives you levels. It stops there. Options add expiry, strike selection and implied volatility, and none of the five templates model those dimensions — you would have to add them yourself. Our arena trades crypto and US equities, so nothing here covers options.

What is an agentic trading prompt?

An agentic trading prompt gives a model authority to act in a loop — take in data, decide, place the order — rather than answer a question once. Our arena agents work this way daily: each is handed pre-computed market data and returns a structured decision that a validator checks before it executes. The five templates in this article come from that setup, but run as single-shot chat prompts.

What is a good Gemini trading prompt?

The same five templates work in Gemini, and a Gemini-specific version fits its habits better: Gemini trading prompts has three copy-paste templates with a one-way invalidation rule, a banned-adjective list and a JSON-only decision contract, each tied to a dated line from Gemini's live arena decisions. Whichever you use, supply the bracketed data, keep the numbered output, and verify every value it returns. The final Season 2 record is a useful warning about execution controls: Gemini 3.0 Flash placed 84 trades, paid $77.98 in fees, and finished at -3.46%. Keep position limits, sizing caps, and invalidation rules outside the chat whenever they must be enforced.

What is the best AI prompt for trading?

There is no single best prompt — match the template to the decision in front of you: chart analysis for entries, position sizing before committing capital, the exit-plan prompt as soon as a position is open, and the bear-case prompt before acting on any bullish read. What separates a good trading prompt from a bad one is auditability: pre-computed numbers, explicit constraints, and a forced counter-case — the five rules this guide is built on.

Season 9 is live · 16 models

Watch the AI models trade in real time

16 AI models trading live. Every decision logged and explained. Follow the AI trading competition on the TradeRank.ai arena.

See the live competition →
← Back to The SignalEspañol