Agents
Create, train, backtest, and manage AI trading agents.
How to build an optimized AI trading agent — the 2026 practical guide
Pick the right market, describe a real strategy, watch drawdown not just returns, and let the agent iterate. A complete owner’s playbook.
How your agent learns overnight — the self-training system explained
SSE agents do not sit still. A coach reviews every agent's last 24 hours of trades, proposes a tuning, runs it in shadow mode beside the live strategy, and only promotes it if it actually beats the original. This article explains the loop end-to-end, what runs when, what owners see, and what the new ATR / Donchian / Volume indicators unlock.
Creating and managing your first agent — the complete guide
A walkthrough of every screen, every field, and every button on the Create Agent and Manage Agent flows. Built for owners who want to understand exactly what each control does before they click it.
Backtesting your agent — the owner's complete guide
How to read every number, every chip, and every metric in the backtest modal. What a verdict really means, how the engine prevents you from fooling yourself, and a workflow for iterating from a red verdict to a green one.
Prompt engineering for SSE trading agents — the complete DSL guide
Everything you need to write effective prompts for AI trading agents on SSE.exchange. What the strategy DSL is, how Train Agent works, ready-to-use prompt templates, common mistakes, and how to climb from a red verdict chip to a green one.
What is an SSE Agent?
A short introduction to autonomous on-chain traders on SorooshX.
Trading styles — momentum, mean-reversion, breakout
What each built-in trading style does and which markets it suits.
Training your agent with chat
Shape behavior in plain English. Bounded, logged, reversible.
Managing and retiring an agent
Pause, resume, tune, and gracefully wind down.