Build a trading strategy in plain English
In DXAP, describe what the agent should consider, when it should stay out and how you want decisions explained. Configure enforceable account and risk limits separately. A useful natural-language strategy gives the agent a decision process rather than a profit target alone.
Published by DXAP, a product of DX Research Group. Updated September 13, 2026.
Write the thesis and exceptions
Name the market scope, the evidence you consider relevant and the conditions that invalidate the idea. Explain what should happen when inputs disagree. “Find profitable trades” leaves almost every decision unspecified; a useful instruction identifies both a reason to act and a reason to wait.
Separate instructions from settings
A request in chat is not a substitute for an asset allowlist, loss limit or approval rule. Review the configured settings in the product. If the agent proposes a settings change, inspect and approve the proposal through the available workflow rather than assuming the text already changed execution authority.
Review the first decisions
Read the agent’s turns and ask how the instruction affected its action or inaction. Refine ambiguous language one issue at a time so you can understand what changed. DXAP’s current user workflow uses real funds; illustrative instructions on this page are not tested strategy presets.
Put it into practice
Illustrative instruction: “Explain the market thesis before proposing a trade. Compare supporting and conflicting evidence. If the thesis is unclear, stay out and explain what would change your assessment. Use only assets allowed in my configured settings.”
Questions about this workflow
Do I need to write code?
DXAP accepts strategy instructions in plain language. You still need to review the account setup, limits and decisions.
Will a prompt enforce a hard loss limit?
Use the product’s policy settings for enforceable limits. Strategy text guides reasoning; it should not be treated as a replacement for those settings.
Read the product details
Run your strategy with DXAP
DXAP is a hosted AI trading agent platform for Hyperliquid traders who want to describe a strategy in plain language, set its limits and inspect its decisions.
No subscription or separate model bill. DXAP charges 2.5 bps (0.025%) on executed agent volume; Hyperliquid fees and funding are separate. Alpha access requires a referral code. The minimum is $10 USDC per agent, with no user paper mode.
Trading can lose money. Examples describe workflows, not expected returns.