Choose a market quote every Monad block

01 · Role in the system

What Jev does here

Jev evaluates the current order-book state and chooses buy or sell for a configured horizon. Ordinary code reads the book, applies position and margin caps, sets the price and size, signs the transaction, tracks receipts, and accounts for fills and P&L. A mock heuristic is the default, so a real Jev run requires explicit configuration.

One judgment per block, everything else in code

The division of labor is the entire design: Jev reads the Kuru MON-USDC order-book snapshot and answers exactly one question — buy or sell for the configured horizon. Everything that makes it a trade is deterministic code: reading the book, applying position and margin caps, setting price and size, signing, tracking receipts, and accounting for fills and P&L.

The default model is a mock heuristic, with real Jev requiring explicit configuration. That is a more honest default than most trading demos ship: the harness is testable without spending judgments, and switching the brain in is a one-line, deliberate act.

A dry run wearing its dryness openly

The limitations say the important thing outright: the public deployment described is a dry run using a mock model, not evidence of live Jev profitability, and a directional judgment controls neither transaction inclusion, nor fills, nor market movement, nor financial risk.

Within those limits the record is the cleanest statement in the trading cluster of the minimal control loop: one bounded direction choice per block over typed state, with a deterministic body that could as easily be driven by any other brain. Comparisons with the desk and paper-trading records in this cluster show what adding indicators, risk appetites, and real orders costs.

02 · Control boundary

Where Jev sits

Order-book snapshot to one bounded direction Choice; deterministic trading code constrains and submits the quote.

Code owns the loop, permissions, thresholds, validation, and side effects. Jev owns only the bounded judgments described above.

03 · Known limits

What this evidence does not prove

• The public deployment described by the repository is a dry run using a mock model, not evidence of live Jev profitability.
• A directional judgment does not control transaction inclusion, fills, market movement, or financial risk.

04 · Attribution

Public sources

This is a Community record: the project was published by a third-party community author.

• jarrodwatts ↗Community · github · public · checked 2026-09-18