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

# evaluator • AI Agent SDK

> Condition Evaluator - Shared condition evaluation logic.

# evaluator

<Badge color="blue">AI Agent</Badge>

Condition Evaluator - Shared condition evaluation logic.

This module provides the shared condition evaluation logic used by both
AgentFlow (string-based conditions) and AgentTeam (dict-based routing).

The implementation is extracted from workflows.py \_evaluate\_condition()
to enable DRY condition handling across the codebase.

## Import

```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
from praisonaiagents.conditions import evaluator
```

## Classes

<CardGroup cols={2}>
  <Card title="ExpressionCondition" icon="brackets-curly" href="../classes/ExpressionCondition">
    String-based condition evaluator for expressions like 'score  80'.
  </Card>

  <Card title="DictCondition" icon="brackets-curly" href="../classes/DictCondition">
    Dict-based condition evaluator for routing decisions.
  </Card>
</CardGroup>

## Functions

<CardGroup cols={2}>
  <Card title="evaluate_condition()" icon="function" href="../functions/evaluate_condition">
    Evaluate a condition expression with variable substitution.
  </Card>
</CardGroup>

***

## Related Documentation

<CardGroup cols={2}>
  <Card title="Evaluation Concept" icon="gavel" href="/docs/concepts/evaluation" />

  <Card title="LLM as Judge" icon="scale-balanced" href="/docs/features/llm-as-judge" />

  <Card title="Evaluation Loop" icon="rotate" href="/docs/eval/evaluation-loop" />
</CardGroup>