If you've never traded and you're looking at AI agents as the entry point, this is the conservative 8-week program. Nothing here is novel — it's the path that experienced traders apply to every new strategy. The reason it's worth writing down is that most beginners skip it, and most beginners then lose money.
Pick a market type. Recurring economic data (CPI, FOMC, jobs report) is friendlier than political contracts because the timing is predictable and there's a consensus to compare against. Pick a single rule you can write in one sentence:
"Enter Kalshi CPI contracts when the implied probability disagrees with the Bloomberg consensus by more than 8 percentage points, and the spread is under 3 cents. Position size: 1% of paper bankroll. Max 4 positions open at once. Daily loss cap: 5% of bankroll."
The first two weeks are not a profit test. They are a translation test: does the agent interpret your rule the way you meant it? Watch every action. If the agent entered when you didn't think the conditions were met, the rule has an ambiguity you need to fix. If it skipped when you thought it should have entered, same — fix the rule.
By week 3 the rule's translation should be clean. Now you're learning whether you can stomach the strategy.
Every rule that wins over a year has weeks where it loses. The math: even a strategy with a true 55% win rate will hit a losing streak of 5 trades roughly every 20 trades. If you would override the agent at trade 4 of that streak, you do not yet have the temperament for this strategy — and the override would convert a normal losing streak into a guaranteed loss.
Watch yourself, not just the agent. If you find yourself reaching for the kill switch every drawdown, the strategy is wrong for you. Pick something with smaller swings.
Open the agent's trade log. For every trade — winning or losing — answer four questions:
If every trade gets four yeses, you have a clean strategy. The P&L over 6 weeks doesn't matter as much as the discipline of the execution. A strategy that loses money cleanly is fixable; a strategy that makes money sloppily will eventually catastrophically lose.
By now, run the agent through at least one scheduled high-volatility event — a CPI release, an FOMC meeting, an election milestone. Volatility is when bad strategies reveal themselves. The contracts you want to inspect most carefully are the ones taken in the 30 minutes around the event.
Did the agent get blown out? Did it size up because "the setup was strong"? Did it ignore the spread widening? Each of these is a sign the rule needs tightening before any live deployment.
If, after 8 weeks of paper, all of these are true, you can consider going live with 5–10% of your intended bankroll:
Believing paper profits mean live profits. They don't necessarily. Live introduces slippage, latency, real-money emotion. The first 4 weeks live is a separate calibration period.
Overriding during a drawdown. A normal losing streak survived becomes a profitable year. A normal losing streak interrupted becomes a guaranteed loss plus the lost upside.
Running multiple strategies at once. Multiplies risk surface, makes attribution impossible, trains you to be inattentive. One strategy until you've mastered it.
Trusting an agent that can be talked past its risk cap. If the LLM ever agrees that "this trade is special, let's exceed the cap," your caps don't exist. Switch platforms.
Going live with full bankroll. First live deployment should be 5–10% of intended size. Live diverges from paper; you want to see how on small money.
Yes if you follow paper-first, one-rule-one-market, audit-every-decision discipline. No if you skip any of those.
5–10% of intended bankroll. First 4 weeks live is calibration; do not put full size behind a strategy that has never traded a real dollar.
Believing paper profits guarantee live profits. Second most common: overriding the agent during a drawdown, which converts a normal losing streak into a guaranteed loss.
One, for at least 6 months. Multiple agents make P&L attribution impossible and multiply risk surface.
Pick something defensible in one sentence with explicit thresholds. "Trade smart on CPI" is not a rule. "Enter when implied probability is 8+ points off consensus and spread is under 3 cents" is.
When you can read any single trade from the last 6 weeks and explain why the agent took it without referring to the P&L. If you can do that, you understand the strategy.
TraderBear ships with paper money on by default. Pick one market, one rule, and audit every decision. Going live takes a deliberate, multi-step opt-in — not a slider.
Adopt a bear →