Small decisions. Interesting possibilities.Submit contentSubmit
Jev-Trades preview

Jev-Trades

Trading bot with the all new TypeSafe AI's first system one model named as Jev.

Added to Jevfast

How it uses Jev

Live one-minute candles and technical indicators are packaged as trading state; Jev returns structured judgments that the Python paper trader applies under configured cash, position, risk-profile, and confidence limits.

What Jev decides

Overbought checkExample answers · not a recorded Jev response · Source ↗
Question 1 · overbought condition
YOUR APP
INSTRUCTION

Do the listed oscillators collectively indicate the instrument is overbought and due for a pause, given price is also near the daily high?

STATE

Current price, oscillators, moving averages, daily high and low, and current position context used by the paper trader.

JEV · NOUL
YesNo

App workflow

  1. Configure paper trading

    Select an asset and configure paper capital, position cap, and risk profile.

  2. Start the selected market

    Apply portfolio settings and explicitly start trading for that asset.

  3. Prepare market state

    Stream candles and compute indicators while the feed is active.

  4. Apply Jev decisions

    When trading is enabled, submit configured state to TypeSafe and apply eligible judgments to the paper portfolio.

  5. Review portfolio activity

    Inspect request/response logs and paper positions.

Why it is interesting

The model makes bounded trading judgments while deterministic portfolio code enforces position sizing and maintains a simulated ledger; the README explicitly says no broker or live order API is connected.