AI Prompt Library for Prop Firm Traders

Prop firm traders operate under constraints most retail traders never face: hard drawdown limits, consistency rules, minimum trading day requirements, and profit targets that must be hit within a fixed window. The FTMO Challenge, for example, reports that fewer than 10% of evaluation attempts result in a funded account. The margin for error is structural, not just psychological.

AI can close that gap — but only if you ask it the right questions. Generic prompts produce generic analysis. A prompt tuned to a 5% max daily drawdown rule, a 10% total drawdown ceiling, and a 10-day minimum trading requirement produces something actionable. The difference is specificity, and specificity is what this library delivers.

Below is a curated set of AI prompts engineered for the prop firm context: evaluation phase discipline, funded account scaling, drawdown recovery, session planning, and rule-compliance checks. Copy them directly into ChatGPT, Claude, or any frontier model. Each prompt is calibrated to the operational reality of trading someone else’s capital under firm-specific constraints.

Why Generic AI Prompts Fail Prop Firm Traders

A retail trader asking AI to ’analyze EUR/USD’ loses nothing if the output is vague. A prop firm trader using that same vague output to size a position during an evaluation phase can breach a daily loss limit and invalidate weeks of work in a single session. The stakes attached to every trade decision are categorically different.

Prop firm rules create hard asymmetries. Missing a profit target by $50 is recoverable. Breaching a drawdown limit by $1 ends the account. AI prompts that don’t encode these asymmetries into the query will return balanced, symmetric advice — which is structurally wrong for this trading environment.

The prompts in this library are built around constraint-first thinking. Every prompt forces the model to account for firm rules, evaluation phase vs. funded phase dynamics, and the behavioral patterns — overtrading after a loss, revenge sizing, late-week desperation trades — that most commonly cause evaluation failures.

• Prop firm evaluations penalize drawdown breaches instantly and permanently — AI output must reflect this asymmetry
• Consistency rules at firms like MyFundedFX and Topstep mean a single outlier day can disqualify an otherwise passing account
• Funded phase scaling introduces new risk parameters that evaluation-phase prompts don’t address
• Psychological pressure during evaluation creates systematic biases — prompts should surface and counter these explicitly

Evaluation Phase: Risk Calibration Prompts

The evaluation phase is where most prop firm capital is lost — by the trader, not the firm. The pressure to hit profit targets accelerates position sizing, compresses analytical time, and creates a feedback loop where losses are followed by larger trades. A well-constructed AI prompt can interrupt this loop before it starts.

The following prompt is designed for the start of each evaluation trading day. It forces explicit acknowledgment of current drawdown status, remaining runway, and the mathematical relationship between position size and daily loss limits. Run it before your first trade, not after your second loss.

I am in Day [X] of a [firm name] evaluation. My account is $[size]. Max daily loss is [amount], max total drawdown is [amount]. I am currently [up/down] $[amount] on the account. Today I plan to trade [instrument] during [session]. Given these constraints, what is the maximum position size I should consider per trade to ensure a single losing trade cannot trigger my daily limit? Also flag any behavioral risks I should monitor given my current P&L position.

Drawdown Recovery Without Rule Violations

Drawing down 60% of your maximum allowable loss before noon is not a crisis — unless you respond to it incorrectly. The correct response is systematic, not reactive. AI can model the math of recovery clearly: what win rate, at what average R, over how many remaining sessions, gets the account back to a passing position without further breaching rules.

The error most traders make is switching strategies mid-evaluation in response to drawdown. A prompt that forces the model to work within your existing edge — rather than brainstorm new approaches — keeps discipline intact when it is most likely to fracture.

Use this prompt after any session where you close down more than 40% of your daily loss limit. It recalibrates expectation without encouraging strategy drift.

I am trading a [firm name] funded evaluation with [X] trading days remaining. My current account balance is $[amount] against a starting balance of $[amount]. My profit target is $[amount] and my max total drawdown floor is $[amount]. My historical win rate is approximately [%] and my average risk-to-reward is [ratio]. Model three recovery scenarios — conservative, base, and aggressive — showing the number of trades and daily P&L required to reach the profit target without breaching the drawdown floor. Flag which scenario introduces unacceptable risk given my win rate.

Session Planning for Funded Account Traders

Passing the evaluation is the first gate. The funded phase introduces a different failure mode: scaling aggression. Traders who pass evaluations often increase size prematurely, treating the funded phase as a reward rather than a second, longer evaluation. Most prop firms include scaling plans with strict conditions — violating them risks losing the funded account before the first payout.

Pre-session planning prompts for funded traders should encode the scaling tier currently active, the payout milestone next in sequence, and the behavioral risk profile of the specific trading session. A Monday London open prompt should look different from a Friday New York close prompt — volatility, liquidity, and psychological fatigue profiles differ materially.

Build a session plan prompt template for each major session type you trade. The five minutes spent running the prompt is five minutes not spent entering a trade on incomplete analysis.

• Specify your current scaling tier and the conditions required to advance — force the model to optimize within those constraints
• Include upcoming high-impact news events and require the model to flag sessions where holding through news violates firm rules
• Ask the model to identify the two or three highest-probability setups for the session — not a comprehensive market overview
• End every session plan prompt with an explicit stop-trading condition: the P&L level or time of day at which you close the platform regardless of open setups

Rule-Compliance Audit Prompts

Prop firm rule sets are dense. FTMO, The Funded Trader, Apex, and E8 Markets each carry distinct restrictions on news trading, overnight holding, weekend positions, and lot size scaling. Traders operating across multiple firm accounts simultaneously — which is common among serious prop traders — routinely confuse rule sets mid-session.

A rule-compliance audit prompt takes your firm’s specific rule document and converts it into a session checklist. Run it once per firm at the start of each month, or whenever you open a new evaluation account. The output should be a short, ranked list of the rules most commonly breached by traders at your experience level — not a full restatement of the terms and conditions.

Below are the key trading rules for my [firm name] account: [paste relevant rules]. I trade [instruments] primarily during [sessions]. My typical hold time is [duration] and I average [X] trades per session. Based on these rules and my trading profile, identify the top five rules I am most likely to accidentally breach. For each, describe the breach scenario in concrete terms and give me a one-sentence pre-trade check I can run to confirm compliance before entering any position.

Building a Personal Prompt Stack for Long-Term Edge

One-off prompts produce one-off insights. The traders extracting the most value from AI are building structured prompt stacks — ordered sequences of queries that cover pre-session planning, in-session decision support, and post-session review. Each layer of the stack feeds the next, creating a feedback loop that compounds analytical quality over time.

For prop firm traders specifically, the post-session review prompt is the most underused. Most traders close the platform after a loss and avoid reviewing the session. A structured post-session prompt forces objective categorization of each trade: was the loss a rule-compliant execution of a valid setup, or a discipline failure? That distinction drives every meaningful improvement in evaluation pass rates.

A complete prompt stack for a prop firm trader covers five layers: market context, session plan, position sizing, real-time decision gates, and post-session review. The full stack takes under 20 minutes to run across a trading day and produces a written record of every analytical decision — which is also the foundation of the trade journal required by most funded trader programs.

• Layer 1 — Market Context: macro bias, key levels, session volatility expectation
• Layer 2 — Session Plan: high-probability setups, news risk flags, stop-trading conditions
• Layer 3 — Position Sizing: drawdown-adjusted size calculation for each planned trade
• Layer 4 — Decision Gates: real-time checklist before each entry, including rule-compliance check
• Layer 5 — Post-Session Review: trade categorization, discipline score, one adjustment for next session