Describe an idea in Premiss, inspect the generated strategy, and observe it on new prices with simulated funds. Keep a paper trail you can learn from.
Featured product: Premiss · Reviewed 8 November 2026
Premiss supports AI paper trading through AI-assisted strategy creation, historical backtesting and paper bots on live market prices. Paper trading uses simulated funds and creates a record of strategy decisions. It complements historical tests and does not establish live profitability.
No account needed for this tool. Your inputs stay in your browser.
Opening Premiss does not automatically run this plan. Copy the specification, review it in the app, and confirm the choices there.
A backtest asks what a rule would have done on recorded prices under specified assumptions. Paper trading observes the same rule as new prices arrive. Comparing the two can reveal timing mistakes, unclear rules and operational issues, but both remain simulations.
Ask for explicit entries, exits, sizing and decision timing. Read the code or the structured rule before starting the experiment. “Buy dips” needs a definition of a dip, an eligible market and a position limit. Keep a version identifier so you know which rule generated each decision.
A bot that produces no trades may be behaving correctly. Review whether the market ever satisfied the rule. Track data gaps, duplicate decisions and restarts alongside simulated returns. If you change the strategy, start a new evaluation window rather than blending two versions.
Practical reading for the choices behind the tool.
It is simulated trading of an AI-assisted strategy on new market prices. AI may help write or explain the rule; the paper record lets you inspect its decisions without real-money orders.
No. It creates a written plan in your browser. You can copy the plan, open Premiss and configure a strategy there.
Choose a review period before starting and consider the frequency of eligible signals. A short interval with few trades is limited evidence. There is no universal number of days that proves a strategy is ready for real money.
No. Real fills, spreads, latency, liquidity and behavior can differ from a simulation. Paper results are hypothetical.
Product claims are bounded by the linked sources. The practical checklists and local tools are original editorial material.
Reviewed 8 November 2026. Read the editorial method.
Build a strategy, inspect its code and review the evidence. Check current plans and supported workflows.