Guardrail Config • AI Agent SDK

GuardrailConfig: Configuration for guardrails and safety validation.

GuardrailConfig

Defined in the Feature Configs module.

AI Agent

Configuration for guardrails and safety validation.

Consolidates: guardrail, max_guardrail_retries, policy

Properties

validator · Optional

No description available.

llm_validator · Optional

No description available.

max_retries · int

No description available.

on_fail · Union

No description available.

policy · Optional

No description available.

policies · List

No description available.

Internal & Generic Methods

• to_dict: Convert to dictionary.

Usage

# With validator function
    Agent(guardrails=my_validator_fn)
    
    # With string preset
    Agent(guardrails="strict")  # Uses strict preset
    
    # With policy strings
    Agent(guardrails=["policy:strict", "pii:redact"])
    
    # With config
    Agent(guardrails=GuardrailConfig(
        validator=my_validator_fn,
        max_retries=3,
        on_fail="retry",
    ))
    
    # With LLM-based validation
    Agent(guardrails=GuardrailConfig(
        llm_validator="Ensure response is helpful and safe",
        max_retries=2,
    ))

Source

View on GitHub

praisonaiagents/config/feature_configs.py at line 382

---

Related Documentation

Guardrails Concept

Guardrails Feature

Approval

Configuration Overview

Agent Config