563
Use Case

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.

1 min readupdated 2026-09-02

/ quick answer

A discretionary trader entered positions without written invalidation levels, then rationalised losses after the fact with no record to review. An assistant that drafts and attacks its own trade plans raised plan completeness to 100% and rejected a fifth of setups on liquidity grounds.

An assistant that drafts and attacks its own trade plans raised plan completeness to 100% and rejected a fifth of setups on liquidity grounds. A discretionary trader entered positions without written invalidation levels, then rationalised losses after the fact with no record to review. Outcome: Every one of 40 subsequent trades had a written invalidation level and size derived from a rule, versus roughly a third before. The risk gate rejected 9 setups outright on liquidity grounds, and the log finally made process review possible separately from PnL. This use case node is part of the Onexial knowledge graph and links to related concepts, workflows and tools below.
Situation
A discretionary trader entered positions without written invalidation levels, then rationalised losses after the fact with no record to review.
Workflow Applied
Outcome
Every one of 40 subsequent trades had a written invalidation level and size derived from a rule, versus roughly a third before. The risk gate rejected 9 setups outright on liquidity grounds, and the log finally made process review possible separately from PnL.
/ frequently asked

What is the Build An AI Trading Assistant use case?

A discretionary trader entered positions without written invalidation levels, then rationalised losses after the fact with no record to review.

What was the outcome?

Every one of 40 subsequent trades had a written invalidation level and size derived from a rule, versus roughly a third before. The risk gate rejected 9 setups outright on liquidity grounds, and the log finally made process review possible separately from PnL.

Which tools were used?

Reasoning LLM with the trading assistant prompt — plan plus adversarial pass, Market and on-chain data APIs — setup context, Deterministic risk calculator — position sizing and liquidity caps, Exchange or Web3 wallet — human execution only; the assistant never signs, Plan-versus-outcome log.

/ 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.

  • Stop Loss & Take Profit

    Stop loss and take profit are pre-committed exit rules that convert a discretionary decision into an executable instruction.

  • Copy Trading

    Copy trading mirrors another trader's or wallet's positions automatically, inheriting both their edge and their risk profile.

  • Hallucination

    When an LLM confidently generates false or fabricated information.

all dictionary

Related workflows

Turn this into a repeatable process.

all workflows

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.

  • Crypto Trading Stack

    Market data, charting, DEX access and a Web3 wallet — the minimum toolset for deliberate on-chain trade execution.

all tool stacks

Related prompts

Reusable prompts for this job.

all prompts

Related use cases

How people apply it, and what came out.

  • Automate Trading Alerts

    Encoding invalidation levels as automated alerts removed screen-watching and caught two thesis breaks the trader would have slept through.

  • Build An AI Crypto Research Agent

    A read-only research agent produced daily briefings on a 30-token watchlist, cutting a 90-minute manual routine to a 10-minute review.

all use cases

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.

  • Manual Trading vs Automated Trading

    Manual trading adapts to context; automation enforces consistency. Most durable setups automate monitoring and keep judgement human.

all comparisons