Write trend-following instructions for an AI agent
A useful trend-following instruction defines what evidence supports continuation, what contradicts it and when the agent should wait. DXAP can interpret a plain-language thesis using available market context, subject to configured limits.
Published by DXAP, a product of DX Research Group. Updated September 13, 2026.
Define the trend you mean
Specify the market scope and the evidence you want considered. Avoid using “strong trend” as the whole strategy. Explain whether a single move is enough or whether the agent should seek supporting context and describe the distinction in its reasoning.
Write the invalidation before entry
Tell the agent what evidence would undermine the thesis. Keep a reason to exit distinct from an enforced policy setting. A model can explain that a thesis weakened, while actual order permissions and risk constraints remain defined by the product configuration.
Make waiting a valid result
A strategy that always demands an opportunity can encourage unnecessary activity. Ask for an explanation when the evidence is mixed. Review several decisions against the instruction rather than treating one outcome as a test of whether trend following works.
An instruction to adapt
Illustrative instruction: “Consider trend continuation only when you can explain supporting market evidence and the strongest counterargument. State what would invalidate the thesis. If the evidence is mixed, wait and explain what is missing. Respect configured asset and risk limits.”
Illustrative wording only. This page does not create an agent or configure its limits.
Questions about this workflow
Is this a tested DXAP strategy preset?
No. It is an illustrative instruction for expressing a decision process. It is not a deployed preset, backtest or return forecast.
Can I require the agent to explain an exit?
You can ask for the reasoning in debriefs and inspect the decision record. Check actual execution separately from the intended exit.
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.