> ## Documentation Index
> Fetch the complete documentation index at: https://docs.argentos.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Simulation Gates

> Test agent behavior against quality benchmarks before allowing deployment.

<Info>
  **ArgentOS Business** -- Simulation gates are part of the Business governance tier.
</Info>

## Overview

Simulation gates are optional quality checkpoints that evaluate agent behavior before allowing deployment. They run test suites against agent policies and score the results across four dimensions.

## Four Component Scores

| Component               | What It Measures                                   |
| ----------------------- | -------------------------------------------------- |
| `objectiveAdherence`    | Does the agent pursue its defined objective?       |
| `boundaryCompliance`    | Does the agent respect neverDo and allowedActions? |
| `escalationCorrectness` | Does the agent escalate at the right times?        |
| `outcomeQuality`        | Are the agent's outputs high quality?              |

Each score is 0-1. The gate aggregates scores across test suites and compares against minimum thresholds.

## Gate Modes

| Mode        | Behavior                                                                                                               |
| ----------- | ---------------------------------------------------------------------------------------------------------------------- |
| **Warn**    | Scores are computed and logged. Agent deploys regardless. Use during initial setup to understand baseline performance. |
| **Enforce** | Scores must meet minimums. Agent deployment is blocked if any component falls below threshold. Use in production.      |

## Configuration

```json theme={null}
{
  "simulationGate": {
    "enabled": true,
    "mode": "enforce",
    "suites": ["support-basic", "escalation-scenarios"],
    "minPassRate": 0.8,
    "minComponentScores": {
      "objectiveAdherence": 0.85,
      "boundaryCompliance": 0.95,
      "escalationCorrectness": 0.80,
      "outcomeQuality": 0.75
    },
    "reportPath": "~/.argentos/reports/simulation/"
  }
}
```

<Tip>
  Simulation gates can be configured globally or per-agent. Agent-level gates override the global gate.
</Tip>

## Worker Wizard Defaults

When creating agents through the Worker Wizard, each template comes with recommended simulation defaults:

| Template         | Boundary Compliance | Escalation Correctness | Outcome Quality | Mode     |
| ---------------- | ------------------- | ---------------------- | --------------- | -------- |
| MSP T1 Support   | 90%                 | 85%                    | 75%             | Enforce  |
| Developer        | 80%                 | 70%                    | 85%             | Warn     |
| Research Analyst | --                  | --                     | --              | Disabled |
| Project Manager  | --                  | --                     | --              | Disabled |

## When to Use

* **New agent deployment** -- verify the agent behaves within policy before going live
* **Policy changes** -- re-run simulations after modifying department or global policies
* **Compliance audits** -- generate reports showing agent adherence to organizational rules
* **Regression testing** -- catch behavior drift after model or config changes

## See Also

* [Intent Governance](/intents/governance) -- the policy engine that simulation gates validate against