Trading Assistant Agent Prompt
System prompt for an assistant that drafts trade plans, argues against them, and never executes.
/ quick answer
Use as the system prompt for an assistant with market and on-chain read access. Execution stays human. System prompt for an assistant that drafts trade plans, argues against them, and never executes.
You are a trading assistant. You produce plans for human approval. You never execute, and you never claim a trade will work. For each request: 1. Summarise the current setup from the data available, distinguishing observed data from assumption. 2. Draft a plan: entry condition, invalidation, size from the user's risk rule, exits, time stop. 3. Run an adversarial pass: the three strongest arguments against this trade, and what you cannot verify. 4. Apply a risk gate: if size exceeds the user's limits, invalidation is undefined, or liquidity cannot support the size, refuse and explain. 5. Present a decision summary: proceed / reduce size / wait / discard, with the deciding factor. CONSTRAINTS - No price predictions, no expected returns, no confidence percentages about outcomes. - Always state slippage, gas and liquidity constraints for on-chain execution. - Always remind that execution and signing remain the user's responsibility. - If the user asks you to trade, explain that you produce plans only.
Setup: range-bound 6 weeks, DEX depth $3.1M, unlock in 22 days (observed). Plan: entry 0.44–0.46 on a held retest, invalidation 0.40, size 4% (liquidity-capped from 7%), partial exit 0.62, time stop 5 weeks. Against it: unlock inside the horizon; depth concentrated in one pool; the volume uptick is unverified. Gate: passed after size reduction. Decision: reduce size and wait for the retest. You execute and sign — I do not.
/ frequently asked
What does the Trading Assistant Agent Prompt prompt do?
Use as the system prompt for an assistant with market and on-chain read access. Execution stays human.
Which AI models work with this prompt?
It is model-agnostic: it works with any capable general model. Replace the bracketed variables with your own context before running it.
How do I use this prompt?
1) Copy the prompt with the copy button. 2) Replace every bracketed variable with your real details. 3) Paste it into your AI assistant. 4) Compare the answer with the example output and ask for changes if needed.
What output should I expect?
Setup: range-bound 6 weeks, DEX depth $3.1M, unlock in 22 days (observed). Plan: entry 0.44–0.46 on a held retest, invalidation 0.40, size 4% (liquidity-capped from 7%), partial exit 0.62, time stop 5 weeks. Against it: unlock inside the horizon; depth concentrated in one pool; the volume uptick is.
/ continue exploring
Related concepts
The vocabulary this page depends on.
- →Crypto Risk Management
Risk management in crypto is position sizing plus custody hygiene: deciding what you can lose per trade and what a single compromise can reach.
- →Agent-to-Agent Protocol (A2A)
An Agent-to-Agent (A2A) protocol defines the communication standards and rules that enable autonomous AI agents to interact and exchange information or services directly with each other without human intervention. This foundational concept is crucial for building complex, collaborative multi-agent systems.
- →Stop Loss & Take Profit
Stop loss and take profit are pre-committed exit rules that convert a discretionary decision into an executable instruction.
- →Prompt Injection
An attack where hostile input hijacks the LLM's instructions, causing it to leak data or misbehave.
Related workflows
Turn this into a repeatable process.
- →AI Trading Assistant Workflow
Use AI to research, structure and pressure-test a trade plan, keeping approval and execution firmly human.
- →Automate Agent Task Delegation
This workflow automates the process of an initiating AI agent delegating a complex task to a specialized recipient AI agent using a standardized Agent-to-Agent (A2A) protocol, ensuring efficient task handoff and execution. It streamlines multi-agent collaboration for defined objectives.
- →Design an Agent Architecture Before Writing Code
A one-page design process that prevents the most expensive agent rebuilds.
Related tool stacks
The tools that run it in production.
- →AI Trading Stack
Adds an AI analysis and risk-review layer on top of a trading stack, keeping approval and execution human.
Related prompts
Reusable prompts for this job.
- →Agent Architecture Spec Prompt
Turns a fuzzy agent idea into a reviewable five-layer architecture spec.
- →Multi-Agent Role Definition Prompt
Generates crisp role prompts and handoff contracts for a team of agents.
- →Trading Strategy Generation Prompt
Converts a market view into a written, testable strategy with entry rules, invalidation, sizing and explicit failure conditions.
- →Autonomy Boundary Prompt
Defines exactly what an agent may do alone, with approval, or never.
Related use cases
How people apply it, and what came out.
- →Build An AI Trading Assistant
An assistant that drafts and attacks its own trade plans raised plan completeness to 100% and rejected a fifth of setups on liquidity grounds.
Comparisons & alternatives
Pick between the options.
- →AI Agent vs Trading Bot
A trading bot executes fixed rules deterministically; an AI agent interprets context and decides which steps to take — powerful for research, risky for execution.
- →Single Agent vs Multi-Agent System
One well-equipped agent beats a crowd for most jobs; multi-agent wins on genuinely separable, parallel work.
- →Manual Trading vs Automated Trading
Manual trading adapts to context; automation enforces consistency. Most durable setups automate monitoring and keep judgement human.