Documentation Index
Fetch the complete documentation index at: https://docs.praison.ai/llms.txt
Use this file to discover all available pages before exploring further.
Guardrails
Validation and safety mechanisms for agent outputs. Supports function-based, LLM-based, and preset guardrails.
Quick Start
from praisonaiagents import Agent
# Simple LLM guardrail (string prompt)
agent = Agent(
description="Write content",
guardrails="Ensure content is safe and accurate"
)
# Function guardrail
def validate(output):
if len(output.raw) < 100:
return (False, "Too short")
return (True, output)
agent = Agent(description="Write content", guardrails=validate)
Feature Usage Table
| Feature | Usage | Example |
|---|
| String preset | guardrails="strict" | Use predefined config |
| Array + overrides | guardrails=["strict", {"max_retries": 10}] | Preset with customization |
| LLM prompt | guardrails="Ensure response is safe..." | Natural language validation |
| Callable | guardrails=my_validator_fn | Function (output) -> (bool, result) |
| Config instance | guardrails=GuardrailConfig(...) | Full control |
| Policy strings | guardrails=["policy:strict", "pii:redact"] | Policy-based validation |
Presets & Options
| Preset | max_retries | on_fail | Description |
|---|
"strict" | 5 | raise | Fail hard on validation errors |
"permissive" | 1 | skip | Skip on failure, continue |
"safety" | 3 | retry | Retry on failure |
Precedence Ladder
Resolution Order: Instance > Config > Array > Dict > String > Bool > DefaultWhen you pass guardrails=, the resolver checks in this order:
- Callable - Function? Use as validator
- Config - GuardrailConfig instance? Use as-is
- Array -
["preset", {"override": value}]? Apply overrides
- Dict -
{"key": value}? Convert to config
- String - Preset name or LLM prompt? Look up or use as prompt
- Bool -
True? Use defaults. False? Disable
String Preset
agent = Agent(description="...", guardrails="strict")
Array with Overrides
agent = Agent(description="...", guardrails=["strict", {"max_retries": 10}])
LLM Prompt (String)
agent = Agent(
description="Write content",
guardrails="Ensure the response is factually accurate and contains no harmful content"
)
Callable Function
def content_length_guardrail(task_output):
if len(task_output.raw) < 100:
return (False, "Content too short")
return (True, task_output)
agent = Agent(description="...", guardrails=content_length_guardrail)
Config Instance
from praisonaiagents import GuardrailConfig
agent = Agent(
description="...",
guardrails=GuardrailConfig(max_retries=5, on_fail="raise")
)
Classes
GuardrailResult
Result of a guardrail validation.
| Attribute | Type | Description |
|---|
success | bool | Whether check passed |
result | str | TaskOutput | Result or error message |
error | str | Error message if failed |
from praisonaiagents import GuardrailResult
# From tuple
result = GuardrailResult.from_tuple((True, task_output))
result = GuardrailResult.from_tuple((False, "Validation failed"))
LLMGuardrail
LLM-powered guardrail using natural language.
from praisonaiagents import LLMGuardrail
guardrail = LLMGuardrail(
description="Ensure content is safe and accurate",
llm="gpt-4o-mini"
)
# Use in agent
agent = Agent(description="...", guardrails=guardrail)
Common Recipes
Function-based Guardrail
from praisonaiagents import Agent, Task, AgentTeam
def validate_length(output):
if len(output.raw) < 100:
return (False, "Too short")
return (True, output)
agent = Agent(description="Write content", guardrails=validate_length)
LLM-based Guardrail
from praisonaiagents import Agent, Task, AgentTeam, LLMGuardrail
# Create an LLM-powered guardrail
quality_guardrail = LLMGuardrail(
description="The content must be professional, factually accurate, and free of grammatical errors",
llm="gpt-4o-mini"
)
agent = Agent(
name="Writer",
role="Content Writer",
goal="Write high-quality content"
)
task = Task(
description="Write a professional article about machine learning",
expected_output="A well-written article",
agent=agent,
guardrails=quality_guardrail
)
agents = AgentTeam(agents=[agent], tasks=[task])
result = agents.start()
Multiple Guardrails
from praisonaiagents import Agent, Task, AgentTeam, LLMGuardrail
def length_check(task_output):
if len(task_output.raw) < 200:
return (False, "Content must be at least 200 characters")
return (True, task_output)
def no_profanity(task_output):
profanity_list = ["bad", "inappropriate"] # simplified example
for word in profanity_list:
if word.lower() in task_output.raw.lower():
return (False, f"Content contains inappropriate language: {word}")
return (True, task_output)
# Chain guardrails
def combined_guardrail(task_output):
# Check length first
success, result = length_check(task_output)
if not success:
return (success, result)
# Then check profanity
return no_profanity(task_output)
task = Task(
description="Write content",
expected_output="Clean, detailed content",
agent=agent,
guardrails=combined_guardrail
)
Best Practices
- Keep guardrails focused - Each guardrail should check one specific aspect
- Provide clear error messages - Help users understand why validation failed
- Use LLM guardrails for complex validation - When rules are hard to express programmatically
- Chain guardrails for multiple checks - Combine simple guardrails for comprehensive validation
- Handle errors gracefully - Guardrails should not crash the application
- Task - Task configuration with guardrails
- Agent - Agent configuration
