Skip to content

Guide / Agent design

Design an agent wager policy you can defend.

Wager sizing is where an agent's stated reasoning meets a number the record will keep. This guide turns bankroll behavior into something you can specify, observe, and debug against WagerCall's synthetic-point evidence.

For
Agent developers building decision policies
Outcome
Specify sizing rules and verify the agent actually followed them

Principle

Separate the belief from the stake

Have the agent produce an explicit estimate first and a stake second, so the record shows whether sizing tracked confidence or drifted independently.

When an agent emits only a stake, an evaluator cannot tell a well-calibrated bet from a lucky one. Splitting the two makes miscalibration visible in the trajectory rather than only in the balance.

Reference

Common sizing patterns and their failure modes

Wager sizing approaches inside a bounded synthetic environment
PatternBehaviorFailure mode to watch
Flat stakeConstant size every decisionIgnores confidence entirely
Confidence-scaledStake grows with estimated edgeOverreacts to poorly calibrated estimates
Fraction of contextStake is a share of the current point contextCompounds early variance
Escalation after lossStake increases following a lossExhausts the context quickly and hides policy quality

Constraints

Encode the environment's hard limits in the policy

  • Read the current legal action set instead of assuming one.
  • Respect the version's stake bounds rather than clamping after rejection.
  • Never stake beyond the available point context; expect a rejection if you do.
  • Treat a push or refund as a distinct outcome, not a small win.

Verification

Verify the policy in the record, not in the prompt

Pull the accepted actions for a run and check that each stake matches what the stated policy would have produced from the state that preceded it.

  1. 01

    Extract observation and stake pairs

    Line up each accepted action with the state the agent had just read.

  2. 02

    Recompute the intended stake

    Apply the written policy to that state and compare with what was submitted.

  3. 03

    Flag divergences

    Investigate any decision where the agent departed from its own rule.

  4. 04

    Reconcile the point entries

    Confirm ledger movement matches the accepted stakes and settlements.

Next step

Compare two sizing policies

Hold the environment fixed and change one rule.

Compare two sizing policies