cai/guardrails/index.html

3091 lines
68 KiB
HTML

<!doctype html>
<html lang="en" class="no-js">
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width,initial-scale=1">
<link rel="prev" href="../context/">
<link rel="next" href="../environment_variables/">
<link rel="icon" href="../assets/imago.png">
<meta name="generator" content="mkdocs-1.6.1, mkdocs-material-9.6.11">
<title>Guardrails & Security - CAI</title>
<link rel="stylesheet" href="../assets/stylesheets/main.4af4bdda.min.css">
<link rel="stylesheet" href="../assets/stylesheets/palette.06af60db.min.css">
<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
<link rel="stylesheet" href="https://fonts.googleapis.com/css?family=Roboto:300,300i,400,400i,700,700i%7CRoboto+Mono:400,400i,700,700i&display=fallback">
<style>:root{--md-text-font:"Roboto";--md-code-font:"Roboto Mono"}</style>
<link rel="stylesheet" href="../assets/_mkdocstrings.css">
<link rel="stylesheet" href="../stylesheets/extra.css">
<script>__md_scope=new URL("..",location),__md_hash=e=>[...e].reduce(((e,_)=>(e<<5)-e+_.charCodeAt(0)),0),__md_get=(e,_=localStorage,t=__md_scope)=>JSON.parse(_.getItem(t.pathname+"."+e)),__md_set=(e,_,t=localStorage,a=__md_scope)=>{try{t.setItem(a.pathname+"."+e,JSON.stringify(_))}catch(e){}}</script>
</head>
<body dir="ltr" data-md-color-scheme="default" data-md-color-primary="custom" data-md-color-accent="indigo">
<input class="md-toggle" data-md-toggle="drawer" type="checkbox" id="__drawer" autocomplete="off">
<input class="md-toggle" data-md-toggle="search" type="checkbox" id="__search" autocomplete="off">
<label class="md-overlay" for="__drawer"></label>
<div data-md-component="skip">
<a href="#guardrails" class="md-skip">
Skip to content
</a>
</div>
<div data-md-component="announce">
</div>
<header class="md-header md-header--shadow" data-md-component="header">
<nav class="md-header__inner md-grid" aria-label="Header">
<a href=".." title="CAI" class="md-header__button md-logo" aria-label="CAI" data-md-component="logo">
<img src="../assets/imago.png" alt="logo">
</a>
<label class="md-header__button md-icon" for="__drawer">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M3 6h18v2H3zm0 5h18v2H3zm0 5h18v2H3z"/></svg>
</label>
<div class="md-header__title" data-md-component="header-title">
<div class="md-header__ellipsis">
<div class="md-header__topic">
<span class="md-ellipsis">
CAI
</span>
</div>
<div class="md-header__topic" data-md-component="header-topic">
<span class="md-ellipsis">
Guardrails & Security
</span>
</div>
</div>
</div>
<label class="md-header__button md-icon" for="__search">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M9.5 3A6.5 6.5 0 0 1 16 9.5c0 1.61-.59 3.09-1.56 4.23l.27.27h.79l5 5-1.5 1.5-5-5v-.79l-.27-.27A6.52 6.52 0 0 1 9.5 16 6.5 6.5 0 0 1 3 9.5 6.5 6.5 0 0 1 9.5 3m0 2C7 5 5 7 5 9.5S7 14 9.5 14 14 12 14 9.5 12 5 9.5 5"/></svg>
</label>
<div class="md-search" data-md-component="search" role="dialog">
<label class="md-search__overlay" for="__search"></label>
<div class="md-search__inner" role="search">
<form class="md-search__form" name="search">
<input type="text" class="md-search__input" name="query" aria-label="Search" placeholder="Search" autocapitalize="off" autocorrect="off" autocomplete="off" spellcheck="false" data-md-component="search-query" required>
<label class="md-search__icon md-icon" for="__search">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M9.5 3A6.5 6.5 0 0 1 16 9.5c0 1.61-.59 3.09-1.56 4.23l.27.27h.79l5 5-1.5 1.5-5-5v-.79l-.27-.27A6.52 6.52 0 0 1 9.5 16 6.5 6.5 0 0 1 3 9.5 6.5 6.5 0 0 1 9.5 3m0 2C7 5 5 7 5 9.5S7 14 9.5 14 14 12 14 9.5 12 5 9.5 5"/></svg>
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M20 11v2H8l5.5 5.5-1.42 1.42L4.16 12l7.92-7.92L13.5 5.5 8 11z"/></svg>
</label>
<nav class="md-search__options" aria-label="Search">
<button type="reset" class="md-search__icon md-icon" title="Clear" aria-label="Clear" tabindex="-1">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M19 6.41 17.59 5 12 10.59 6.41 5 5 6.41 10.59 12 5 17.59 6.41 19 12 13.41 17.59 19 19 17.59 13.41 12z"/></svg>
</button>
</nav>
</form>
<div class="md-search__output">
<div class="md-search__scrollwrap" tabindex="0" data-md-scrollfix>
<div class="md-search-result" data-md-component="search-result">
<div class="md-search-result__meta">
Initializing search
</div>
<ol class="md-search-result__list" role="presentation"></ol>
</div>
</div>
</div>
</div>
</div>
<div class="md-header__source">
<a href="https://github.com/aliasrobotics/cai" title="Go to repository" class="md-source" data-md-component="source">
<div class="md-source__icon md-icon">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 496 512"><!--! Font Awesome Free 6.7.2 by @fontawesome - https://fontawesome.com License - https://fontawesome.com/license/free (Icons: CC BY 4.0, Fonts: SIL OFL 1.1, Code: MIT License) Copyright 2024 Fonticons, Inc.--><path d="M165.9 397.4c0 2-2.3 3.6-5.2 3.6-3.3.3-5.6-1.3-5.6-3.6 0-2 2.3-3.6 5.2-3.6 3-.3 5.6 1.3 5.6 3.6m-31.1-4.5c-.7 2 1.3 4.3 4.3 4.9 2.6 1 5.6 0 6.2-2s-1.3-4.3-4.3-5.2c-2.6-.7-5.5.3-6.2 2.3m44.2-1.7c-2.9.7-4.9 2.6-4.6 4.9.3 2 2.9 3.3 5.9 2.6 2.9-.7 4.9-2.6 4.6-4.6-.3-1.9-3-3.2-5.9-2.9M244.8 8C106.1 8 0 113.3 0 252c0 110.9 69.8 205.8 169.5 239.2 12.8 2.3 17.3-5.6 17.3-12.1 0-6.2-.3-40.4-.3-61.4 0 0-70 15-84.7-29.8 0 0-11.4-29.1-27.8-36.6 0 0-22.9-15.7 1.6-15.4 0 0 24.9 2 38.6 25.8 21.9 38.6 58.6 27.5 72.9 20.9 2.3-16 8.8-27.1 16-33.7-55.9-6.2-112.3-14.3-112.3-110.5 0-27.5 7.6-41.3 23.6-58.9-2.6-6.5-11.1-33.3 2.6-67.9 20.9-6.5 69 27 69 27 20-5.6 41.5-8.5 62.8-8.5s42.8 2.9 62.8 8.5c0 0 48.1-33.6 69-27 13.7 34.7 5.2 61.4 2.6 67.9 16 17.7 25.8 31.5 25.8 58.9 0 96.5-58.9 104.2-114.8 110.5 9.2 7.9 17 22.9 17 46.4 0 33.7-.3 75.4-.3 83.6 0 6.5 4.6 14.4 17.3 12.1C428.2 457.8 496 362.9 496 252 496 113.3 383.5 8 244.8 8M97.2 352.9c-1.3 1-1 3.3.7 5.2 1.6 1.6 3.9 2.3 5.2 1 1.3-1 1-3.3-.7-5.2-1.6-1.6-3.9-2.3-5.2-1m-10.8-8.1c-.7 1.3.3 2.9 2.3 3.9 1.6 1 3.6.7 4.3-.7.7-1.3-.3-2.9-2.3-3.9-2-.6-3.6-.3-4.3.7m32.4 35.6c-1.6 1.3-1 4.3 1.3 6.2 2.3 2.3 5.2 2.6 6.5 1 1.3-1.3.7-4.3-1.3-6.2-2.2-2.3-5.2-2.6-6.5-1m-11.4-14.7c-1.6 1-1.6 3.6 0 5.9s4.3 3.3 5.6 2.3c1.6-1.3 1.6-3.9 0-6.2-1.4-2.3-4-3.3-5.6-2"/></svg>
</div>
<div class="md-source__repository">
aliasrobotics/cai
</div>
</a>
</div>
</nav>
</header>
<div class="md-container" data-md-component="container">
<main class="md-main" data-md-component="main">
<div class="md-main__inner md-grid">
<div class="md-sidebar md-sidebar--primary" data-md-component="sidebar" data-md-type="navigation" >
<div class="md-sidebar__scrollwrap">
<div class="md-sidebar__inner">
<nav class="md-nav md-nav--primary" aria-label="Navigation" data-md-level="0">
<label class="md-nav__title" for="__drawer">
<a href=".." title="CAI" class="md-nav__button md-logo" aria-label="CAI" data-md-component="logo">
<img src="../assets/imago.png" alt="logo">
</a>
CAI
</label>
<div class="md-nav__source">
<a href="https://github.com/aliasrobotics/cai" title="Go to repository" class="md-source" data-md-component="source">
<div class="md-source__icon md-icon">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 496 512"><!--! Font Awesome Free 6.7.2 by @fontawesome - https://fontawesome.com License - https://fontawesome.com/license/free (Icons: CC BY 4.0, Fonts: SIL OFL 1.1, Code: MIT License) Copyright 2024 Fonticons, Inc.--><path d="M165.9 397.4c0 2-2.3 3.6-5.2 3.6-3.3.3-5.6-1.3-5.6-3.6 0-2 2.3-3.6 5.2-3.6 3-.3 5.6 1.3 5.6 3.6m-31.1-4.5c-.7 2 1.3 4.3 4.3 4.9 2.6 1 5.6 0 6.2-2s-1.3-4.3-4.3-5.2c-2.6-.7-5.5.3-6.2 2.3m44.2-1.7c-2.9.7-4.9 2.6-4.6 4.9.3 2 2.9 3.3 5.9 2.6 2.9-.7 4.9-2.6 4.6-4.6-.3-1.9-3-3.2-5.9-2.9M244.8 8C106.1 8 0 113.3 0 252c0 110.9 69.8 205.8 169.5 239.2 12.8 2.3 17.3-5.6 17.3-12.1 0-6.2-.3-40.4-.3-61.4 0 0-70 15-84.7-29.8 0 0-11.4-29.1-27.8-36.6 0 0-22.9-15.7 1.6-15.4 0 0 24.9 2 38.6 25.8 21.9 38.6 58.6 27.5 72.9 20.9 2.3-16 8.8-27.1 16-33.7-55.9-6.2-112.3-14.3-112.3-110.5 0-27.5 7.6-41.3 23.6-58.9-2.6-6.5-11.1-33.3 2.6-67.9 20.9-6.5 69 27 69 27 20-5.6 41.5-8.5 62.8-8.5s42.8 2.9 62.8 8.5c0 0 48.1-33.6 69-27 13.7 34.7 5.2 61.4 2.6 67.9 16 17.7 25.8 31.5 25.8 58.9 0 96.5-58.9 104.2-114.8 110.5 9.2 7.9 17 22.9 17 46.4 0 33.7-.3 75.4-.3 83.6 0 6.5 4.6 14.4 17.3 12.1C428.2 457.8 496 362.9 496 252 496 113.3 383.5 8 244.8 8M97.2 352.9c-1.3 1-1 3.3.7 5.2 1.6 1.6 3.9 2.3 5.2 1 1.3-1 1-3.3-.7-5.2-1.6-1.6-3.9-2.3-5.2-1m-10.8-8.1c-.7 1.3.3 2.9 2.3 3.9 1.6 1 3.6.7 4.3-.7.7-1.3-.3-2.9-2.3-3.9-2-.6-3.6-.3-4.3.7m32.4 35.6c-1.6 1.3-1 4.3 1.3 6.2 2.3 2.3 5.2 2.6 6.5 1 1.3-1.3.7-4.3-1.3-6.2-2.2-2.3-5.2-2.6-6.5-1m-11.4-14.7c-1.6 1-1.6 3.6 0 5.9s4.3 3.3 5.6 2.3c1.6-1.3 1.6-3.9 0-6.2-1.4-2.3-4-3.3-5.6-2"/></svg>
</div>
<div class="md-source__repository">
aliasrobotics/cai
</div>
</a>
</div>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item md-nav__item--section md-nav__item--nested">
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_1" >
<label class="md-nav__link" for="__nav_1" id="__nav_1_label" tabindex="">
<span class="md-ellipsis">
Getting Started
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_1_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_1">
<span class="md-nav__icon md-icon"></span>
Getting Started
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href=".." class="md-nav__link">
<span class="md-ellipsis">
Welcome
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../cai_installation/" class="md-nav__link">
<span class="md-ellipsis">
Installation
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../cai_quickstart/" class="md-nav__link">
<span class="md-ellipsis">
Quickstart
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../cai_list_of_models/" class="md-nav__link">
<span class="md-ellipsis">
Available Models
</span>
</a>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_1_5" >
<label class="md-nav__link" for="__nav_1_5" id="__nav_1_5_label" tabindex="0">
<span class="md-ellipsis">
Model Providers
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="2" aria-labelledby="__nav_1_5_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_1_5">
<span class="md-nav__icon md-icon"></span>
Model Providers
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../providers/openrouter.md" class="md-nav__link">
<span class="md-ellipsis">
OpenRouter
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../providers/ollama/" class="md-nav__link">
<span class="md-ellipsis">
Ollama
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../providers/azure.md" class="md-nav__link">
<span class="md-ellipsis">
Azure OpenAI
</span>
</a>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="../cai_pro/" class="md-nav__link">
<span class="md-ellipsis">
🚀 CAI PRO
</span>
</a>
</li>
<li class="md-nav__item md-nav__item--section md-nav__item--nested">
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_3" >
<label class="md-nav__link" for="__nav_3" id="__nav_3_label" tabindex="">
<span class="md-ellipsis">
Core Concepts
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_3_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_3">
<span class="md-nav__icon md-icon"></span>
Core Concepts
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../cai_architecture/" class="md-nav__link">
<span class="md-ellipsis">
Architecture
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../agents/" class="md-nav__link">
<span class="md-ellipsis">
Agents
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../tools/" class="md-nav__link">
<span class="md-ellipsis">
Tools
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../handoffs/" class="md-nav__link">
<span class="md-ellipsis">
Handoffs
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../multi_agent/" class="md-nav__link">
<span class="md-ellipsis">
Multi-Agent Systems
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--section md-nav__item--nested">
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_4" >
<label class="md-nav__link" for="__nav_4" id="__nav_4_label" tabindex="">
<span class="md-ellipsis">
Benchmarking
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_4_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_4">
<span class="md-nav__icon md-icon"></span>
Benchmarking
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../benchmarking/overview/" class="md-nav__link">
<span class="md-ellipsis">
Overview
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../benchmarking/running_benchmarks/" class="md-nav__link">
<span class="md-ellipsis">
Running Benchmarks
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../benchmarking/attack_defense/" class="md-nav__link">
<span class="md-ellipsis">
Attack & Defense CTFs
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../benchmarking/jeopardy_ctfs/" class="md-nav__link">
<span class="md-ellipsis">
Jeopardy CTFs
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../benchmarking/cyber_ranges/" class="md-nav__link">
<span class="md-ellipsis">
Cyber Ranges
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../benchmarking/knowledge_benchmarks/" class="md-nav__link">
<span class="md-ellipsis">
Knowledge Benchmarks
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../benchmarking/privacy_benchmarks/" class="md-nav__link">
<span class="md-ellipsis">
Privacy Benchmarks
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--active md-nav__item--section md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_5" checked>
<label class="md-nav__link" for="__nav_5" id="__nav_5_label" tabindex="">
<span class="md-ellipsis">
Guides
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_5_label" aria-expanded="true">
<label class="md-nav__title" for="__nav_5">
<span class="md-nav__icon md-icon"></span>
Guides
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../running_agents/" class="md-nav__link">
<span class="md-ellipsis">
Running Agents
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../continue_mode/" class="md-nav__link">
<span class="md-ellipsis">
Continue Mode
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../results/" class="md-nav__link">
<span class="md-ellipsis">
Working with Results
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../streaming/" class="md-nav__link">
<span class="md-ellipsis">
Streaming
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../tracing/" class="md-nav__link">
<span class="md-ellipsis">
Tracing & Debugging
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../context/" class="md-nav__link">
<span class="md-ellipsis">
Context Management
</span>
</a>
</li>
<li class="md-nav__item md-nav__item--active">
<input class="md-nav__toggle md-toggle" type="checkbox" id="__toc">
<label class="md-nav__link md-nav__link--active" for="__toc">
<span class="md-ellipsis">
Guardrails & Security
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<a href="./" class="md-nav__link md-nav__link--active">
<span class="md-ellipsis">
Guardrails & Security
</span>
</a>
<nav class="md-nav md-nav--secondary" aria-label="Table of contents">
<label class="md-nav__title" for="__toc">
<span class="md-nav__icon md-icon"></span>
Table of contents
</label>
<ul class="md-nav__list" data-md-component="toc" data-md-scrollfix>
<li class="md-nav__item">
<a href="#input-guardrails" class="md-nav__link">
<span class="md-ellipsis">
Input guardrails
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#output-guardrails" class="md-nav__link">
<span class="md-ellipsis">
Output guardrails
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#tripwires" class="md-nav__link">
<span class="md-ellipsis">
Tripwires
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#implementing-a-guardrail" class="md-nav__link">
<span class="md-ellipsis">
Implementing a guardrail
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="../environment_variables/" class="md-nav__link">
<span class="md-ellipsis">
Environment Variables
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../cai/getting-started/packet_capture_wsl/" class="md-nav__link">
<span class="md-ellipsis">
Packet Capture on WSL2
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--section md-nav__item--nested">
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_6" >
<label class="md-nav__link" for="__nav_6" id="__nav_6_label" tabindex="">
<span class="md-ellipsis">
Troubleshooting
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_6_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_6">
<span class="md-nav__icon md-icon"></span>
Troubleshooting
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../cai/troubleshooting/operator_feedback_reproduction/" class="md-nav__link">
<span class="md-ellipsis">
Operator Feedback Reproduction
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../cai/troubleshooting/platform_limitations/" class="md-nav__link">
<span class="md-ellipsis">
Platform Limitations
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--section md-nav__item--nested">
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_7" >
<label class="md-nav__link" for="__nav_7" id="__nav_7_label" tabindex="">
<span class="md-ellipsis">
Case Studies
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_7_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_7">
<span class="md-nav__icon md-icon"></span>
Case Studies
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../cai/case-studies/operator-artifact-evidence/" class="md-nav__link">
<span class="md-ellipsis">
Operator Artifact Evidence
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--section md-nav__item--nested">
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_8" >
<label class="md-nav__link" for="__nav_8" id="__nav_8_label" tabindex="">
<span class="md-ellipsis">
Mobile UI (iOS)
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_8_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_8">
<span class="md-nav__icon md-icon"></span>
Mobile UI (iOS)
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../mui/mui_index/" class="md-nav__link">
<span class="md-ellipsis">
Overview
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../mui/getting_started/" class="md-nav__link">
<span class="md-ellipsis">
Getting Started
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../mui/user_interface/" class="md-nav__link">
<span class="md-ellipsis">
User Interface
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../mui/gestures_shortcuts/" class="md-nav__link">
<span class="md-ellipsis">
Gestures & Shortcuts
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../mui/chat_features/" class="md-nav__link">
<span class="md-ellipsis">
Chat Features
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--section md-nav__item--nested">
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_9" >
<label class="md-nav__link" for="__nav_9" id="__nav_9_label" tabindex="">
<span class="md-ellipsis">
Terminal UI (TUI) - Deprecated
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_9_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_9">
<span class="md-nav__icon md-icon"></span>
Terminal UI (TUI) - Deprecated
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../tui/tui_index/" class="md-nav__link">
<span class="md-ellipsis">
Overview
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../tui/getting_started/" class="md-nav__link">
<span class="md-ellipsis">
Getting Started
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../tui/user_interface/" class="md-nav__link">
<span class="md-ellipsis">
User Interface
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../tui/terminals_management/" class="md-nav__link">
<span class="md-ellipsis">
Terminals Management
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../tui/teams_and_parallel_execution/" class="md-nav__link">
<span class="md-ellipsis">
Teams & Parallel Execution
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../tui/sidebar_features/" class="md-nav__link">
<span class="md-ellipsis">
Sidebar Features
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../tui/keyboard_shortcuts/" class="md-nav__link">
<span class="md-ellipsis">
Keyboard Shortcuts
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../tui/commands_reference/" class="md-nav__link">
<span class="md-ellipsis">
Commands Reference
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../tui/advanced_features/" class="md-nav__link">
<span class="md-ellipsis">
Advanced Features
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../tui/troubleshooting/" class="md-nav__link">
<span class="md-ellipsis">
Troubleshooting
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--section md-nav__item--nested">
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_10" >
<label class="md-nav__link" for="__nav_10" id="__nav_10_label" tabindex="">
<span class="md-ellipsis">
API Reference
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_10_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_10">
<span class="md-nav__icon md-icon"></span>
API Reference
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_10_1" >
<label class="md-nav__link" for="__nav_10_1" id="__nav_10_1_label" tabindex="0">
<span class="md-ellipsis">
Agents
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="2" aria-labelledby="__nav_10_1_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_10_1">
<span class="md-nav__icon md-icon"></span>
Agents
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../ref/agent/" class="md-nav__link">
<span class="md-ellipsis">
Agent
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../ref/run/" class="md-nav__link">
<span class="md-ellipsis">
Runner
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../ref/tool/" class="md-nav__link">
<span class="md-ellipsis">
Tool
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../ref/result/" class="md-nav__link">
<span class="md-ellipsis">
Result
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../ref/stream_events/" class="md-nav__link">
<span class="md-ellipsis">
Stream Events
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../ref/handoffs/" class="md-nav__link">
<span class="md-ellipsis">
Handoffs
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../ref/lifecycle/" class="md-nav__link">
<span class="md-ellipsis">
Lifecycle
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../ref/items/" class="md-nav__link">
<span class="md-ellipsis">
Items
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../ref/run_context/" class="md-nav__link">
<span class="md-ellipsis">
Run Context
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../ref/usage/" class="md-nav__link">
<span class="md-ellipsis">
Usage
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../ref/exceptions/" class="md-nav__link">
<span class="md-ellipsis">
Exceptions
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../ref/guardrail/" class="md-nav__link">
<span class="md-ellipsis">
Guardrail
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../ref/model_settings/" class="md-nav__link">
<span class="md-ellipsis">
Model Settings
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../ref/agent_output/" class="md-nav__link">
<span class="md-ellipsis">
Agent Output
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../ref/function_schema/" class="md-nav__link">
<span class="md-ellipsis">
Function Schema
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_10_2" >
<label class="md-nav__link" for="__nav_10_2" id="__nav_10_2_label" tabindex="0">
<span class="md-ellipsis">
Models
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="2" aria-labelledby="__nav_10_2_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_10_2">
<span class="md-nav__icon md-icon"></span>
Models
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../ref/models/interface/" class="md-nav__link">
<span class="md-ellipsis">
Interface
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../ref/models/openai_chatcompletions/" class="md-nav__link">
<span class="md-ellipsis">
OpenAI Chat Completions
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../ref/models/openai_responses/" class="md-nav__link">
<span class="md-ellipsis">
OpenAI Responses
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_10_3" >
<label class="md-nav__link" for="__nav_10_3" id="__nav_10_3_label" tabindex="0">
<span class="md-ellipsis">
Extensions
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="2" aria-labelledby="__nav_10_3_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_10_3">
<span class="md-nav__icon md-icon"></span>
Extensions
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../ref/extensions/handoff_filters/" class="md-nav__link">
<span class="md-ellipsis">
Handoff Filters
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../ref/extensions/handoff_prompt/" class="md-nav__link">
<span class="md-ellipsis">
Handoff Prompt
</span>
</a>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--section md-nav__item--nested">
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_11" >
<label class="md-nav__link" for="__nav_11" id="__nav_11_label" tabindex="">
<span class="md-ellipsis">
Advanced
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_11_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_11">
<span class="md-nav__icon md-icon"></span>
Advanced
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../cai_development/" class="md-nav__link">
<span class="md-ellipsis">
Development
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--section md-nav__item--nested">
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_12" >
<label class="md-nav__link" for="__nav_12" id="__nav_12_label" tabindex="">
<span class="md-ellipsis">
Research
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_12_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_12">
<span class="md-nav__icon md-icon"></span>
Research
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../research/" class="md-nav__link">
<span class="md-ellipsis">
Overview
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--section md-nav__item--nested">
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_13" >
<label class="md-nav__link" for="__nav_13" id="__nav_13_label" tabindex="">
<span class="md-ellipsis">
Resources
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_13_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_13">
<span class="md-nav__icon md-icon"></span>
Resources
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../cai_faq/" class="md-nav__link">
<span class="md-ellipsis">
FAQ
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../cai_find_us/" class="md-nav__link">
<span class="md-ellipsis">
Find Us
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../cai_citation_and_acknowledgments/" class="md-nav__link">
<span class="md-ellipsis">
Citation & Acknowledgments
</span>
</a>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</div>
</div>
</div>
<div class="md-sidebar md-sidebar--secondary" data-md-component="sidebar" data-md-type="toc" >
<div class="md-sidebar__scrollwrap">
<div class="md-sidebar__inner">
<nav class="md-nav md-nav--secondary" aria-label="Table of contents">
<label class="md-nav__title" for="__toc">
<span class="md-nav__icon md-icon"></span>
Table of contents
</label>
<ul class="md-nav__list" data-md-component="toc" data-md-scrollfix>
<li class="md-nav__item">
<a href="#input-guardrails" class="md-nav__link">
<span class="md-ellipsis">
Input guardrails
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#output-guardrails" class="md-nav__link">
<span class="md-ellipsis">
Output guardrails
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#tripwires" class="md-nav__link">
<span class="md-ellipsis">
Tripwires
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#implementing-a-guardrail" class="md-nav__link">
<span class="md-ellipsis">
Implementing a guardrail
</span>
</a>
</li>
</ul>
</nav>
</div>
</div>
</div>
<div class="md-content" data-md-component="content">
<article class="md-content__inner md-typeset">
<h1 id="guardrails">Guardrails</h1>
<p>Guardrails run <em>in parallel</em> to your agents, enabling you to do checks and validations of user input. For example, imagine you have an agent that uses a very smart (and hence slow/expensive) model to help with customer requests. You wouldn't want malicious users to ask the model to help them with their math homework. So, you can run a guardrail with a fast/cheap model. If the guardrail detects malicious usage, it can immediately raise an error, which stops the expensive model from running and saves you time/money.</p>
<p>There are two kinds of guardrails:</p>
<ol>
<li>Input guardrails run on the initial user input</li>
<li>Output guardrails run on the final agent output</li>
</ol>
<h2 id="input-guardrails">Input guardrails</h2>
<p>Input guardrails run in 3 steps:</p>
<ol>
<li>First, the guardrail receives the same input passed to the agent.</li>
<li>Next, the guardrail function runs to produce a <a class="autorefs autorefs-internal" title="GuardrailFunctionOutput
dataclass
" href="../ref/guardrail/#cai.sdk.agents.guardrail.GuardrailFunctionOutput"><code>GuardrailFunctionOutput</code></a>, which is then wrapped in an <a class="autorefs autorefs-internal" title="InputGuardrailResult
dataclass
" href="../ref/guardrail/#cai.sdk.agents.guardrail.InputGuardrailResult"><code>InputGuardrailResult</code></a></li>
<li>Finally, we check if <a class="autorefs autorefs-internal" title="tripwire_triggered
instance-attribute
" href="../ref/guardrail/#cai.sdk.agents.guardrail.GuardrailFunctionOutput.tripwire_triggered"><code>.tripwire_triggered</code></a> is true. If true, an <a class="autorefs autorefs-internal" title="InputGuardrailTripwireTriggered" href="../ref/exceptions/#cai.sdk.agents.exceptions.InputGuardrailTripwireTriggered"><code>InputGuardrailTripwireTriggered</code></a> exception is raised, so you can appropriately respond to the user or handle the exception.</li>
</ol>
<div class="admonition note">
<p class="admonition-title">Note</p>
<p>Input guardrails are intended to run on user input, so an agent's guardrails only run if the agent is the <em>first</em> agent. You might wonder, why is the <code>guardrails</code> property on the agent instead of passed to <code>Runner.run</code>? It's because guardrails tend to be related to the actual Agent - you'd run different guardrails for different agents, so colocating the code is useful for readability.</p>
</div>
<h2 id="output-guardrails">Output guardrails</h2>
<p>Output guardrails run in 3 steps:</p>
<ol>
<li>First, the guardrail receives the same input passed to the agent.</li>
<li>Next, the guardrail function runs to produce a <a class="autorefs autorefs-internal" title="GuardrailFunctionOutput
dataclass
" href="../ref/guardrail/#cai.sdk.agents.guardrail.GuardrailFunctionOutput"><code>GuardrailFunctionOutput</code></a>, which is then wrapped in an <a class="autorefs autorefs-internal" title="OutputGuardrailResult
dataclass
" href="../ref/guardrail/#cai.sdk.agents.guardrail.OutputGuardrailResult"><code>OutputGuardrailResult</code></a></li>
<li>Finally, we check if <a class="autorefs autorefs-internal" title="tripwire_triggered
instance-attribute
" href="../ref/guardrail/#cai.sdk.agents.guardrail.GuardrailFunctionOutput.tripwire_triggered"><code>.tripwire_triggered</code></a> is true. If true, an <a class="autorefs autorefs-internal" title="OutputGuardrailTripwireTriggered" href="../ref/exceptions/#cai.sdk.agents.exceptions.OutputGuardrailTripwireTriggered"><code>OutputGuardrailTripwireTriggered</code></a> exception is raised, so you can appropriately respond to the user or handle the exception.</li>
</ol>
<div class="admonition note">
<p class="admonition-title">Note</p>
<p>Output guardrails are intended to run on the final agent output, so an agent's guardrails only run if the agent is the <em>last</em> agent. Similar to the input guardrails, we do this because guardrails tend to be related to the actual Agent - you'd run different guardrails for different agents, so colocating the code is useful for readability.</p>
</div>
<h2 id="tripwires">Tripwires</h2>
<p>If the input or output fails the guardrail, the Guardrail can signal this with a tripwire. As soon as we see a guardrail that has triggered the tripwires, we immediately raise a <code>{Input,Output}GuardrailTripwireTriggered</code> exception and halt the Agent execution.</p>
<h2 id="implementing-a-guardrail">Implementing a guardrail</h2>
<p>You need to provide a function that receives input, and returns a <a class="autorefs autorefs-internal" title="GuardrailFunctionOutput
dataclass
" href="../ref/guardrail/#cai.sdk.agents.guardrail.GuardrailFunctionOutput"><code>GuardrailFunctionOutput</code></a>. In this example, we'll do this by running an Agent under the hood.</p>
<div class="language-python highlight"><pre><span></span><code><span id="__span-0-1"><span class="kn">from</span><span class="w"> </span><span class="nn">pydantic</span><span class="w"> </span><span class="kn">import</span> <span class="n">BaseModel</span>
</span><span id="__span-0-2"><span class="kn">from</span><span class="w"> </span><span class="nn">cai.sdk.agents</span><span class="w"> </span><span class="kn">import</span> <span class="p">(</span>
</span><span id="__span-0-3"> <span class="n">Agent</span><span class="p">,</span>
</span><span id="__span-0-4"> <span class="n">GuardrailFunctionOutput</span><span class="p">,</span>
</span><span id="__span-0-5"> <span class="n">InputGuardrailTripwireTriggered</span><span class="p">,</span>
</span><span id="__span-0-6"> <span class="n">RunContextWrapper</span><span class="p">,</span>
</span><span id="__span-0-7"> <span class="n">Runner</span><span class="p">,</span>
</span><span id="__span-0-8"> <span class="n">TResponseInputItem</span><span class="p">,</span>
</span><span id="__span-0-9"> <span class="n">input_guardrail</span><span class="p">,</span>
</span><span id="__span-0-10"><span class="p">)</span>
</span><span id="__span-0-11">
</span><span id="__span-0-12"><span class="k">class</span><span class="w"> </span><span class="nc">MaliciousRequestOutput</span><span class="p">(</span><span class="n">BaseModel</span><span class="p">):</span>
</span><span id="__span-0-13"> <span class="n">is_malicious_request</span><span class="p">:</span> <span class="nb">bool</span>
</span><span id="__span-0-14"> <span class="n">reasoning</span><span class="p">:</span> <span class="nb">str</span>
</span><span id="__span-0-15">
</span><span id="__span-0-16"><span class="n">guardrail_agent</span> <span class="o">=</span> <span class="n">Agent</span><span class="p">(</span> <span class="c1"># (1)!</span>
</span><span id="__span-0-17"> <span class="n">name</span><span class="o">=</span><span class="s2">&quot;Security Guardrail Check&quot;</span><span class="p">,</span>
</span><span id="__span-0-18"> <span class="n">instructions</span><span class="o">=</span><span class="s2">&quot;Check if the user is asking for help with hacking or bypassing security systems.&quot;</span><span class="p">,</span>
</span><span id="__span-0-19"> <span class="n">output_type</span><span class="o">=</span><span class="n">MaliciousRequestOutput</span><span class="p">,</span>
</span><span id="__span-0-20"><span class="p">)</span>
</span><span id="__span-0-21">
</span><span id="__span-0-22">
</span><span id="__span-0-23"><span class="nd">@input_guardrail</span>
</span><span id="__span-0-24"><span class="k">async</span> <span class="k">def</span><span class="w"> </span><span class="nf">security_guardrail</span><span class="p">(</span> <span class="c1"># (2)!</span>
</span><span id="__span-0-25"> <span class="n">ctx</span><span class="p">:</span> <span class="n">RunContextWrapper</span><span class="p">[</span><span class="kc">None</span><span class="p">],</span> <span class="n">agent</span><span class="p">:</span> <span class="n">Agent</span><span class="p">,</span> <span class="nb">input</span><span class="p">:</span> <span class="nb">str</span> <span class="o">|</span> <span class="nb">list</span><span class="p">[</span><span class="n">TResponseInputItem</span><span class="p">]</span>
</span><span id="__span-0-26"><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">GuardrailFunctionOutput</span><span class="p">:</span>
</span><span id="__span-0-27"> <span class="n">result</span> <span class="o">=</span> <span class="k">await</span> <span class="n">Runner</span><span class="o">.</span><span class="n">run</span><span class="p">(</span><span class="n">guardrail_agent</span><span class="p">,</span> <span class="nb">input</span><span class="p">,</span> <span class="n">context</span><span class="o">=</span><span class="n">ctx</span><span class="o">.</span><span class="n">context</span><span class="p">)</span>
</span><span id="__span-0-28">
</span><span id="__span-0-29"> <span class="k">return</span> <span class="n">GuardrailFunctionOutput</span><span class="p">(</span>
</span><span id="__span-0-30"> <span class="n">output_info</span><span class="o">=</span><span class="n">result</span><span class="o">.</span><span class="n">final_output</span><span class="p">,</span> <span class="c1"># (3)!</span>
</span><span id="__span-0-31"> <span class="n">tripwire_triggered</span><span class="o">=</span><span class="n">result</span><span class="o">.</span><span class="n">final_output</span><span class="o">.</span><span class="n">is_malicious_request</span><span class="p">,</span>
</span><span id="__span-0-32"> <span class="p">)</span>
</span><span id="__span-0-33">
</span><span id="__span-0-34">
</span><span id="__span-0-35"><span class="n">agent</span> <span class="o">=</span> <span class="n">Agent</span><span class="p">(</span> <span class="c1"># (4)!</span>
</span><span id="__span-0-36"> <span class="n">name</span><span class="o">=</span><span class="s2">&quot;Security assistant&quot;</span><span class="p">,</span>
</span><span id="__span-0-37"> <span class="n">instructions</span><span class="o">=</span><span class="s2">&quot;You are a security assistant. You help users with legitimate security questions.&quot;</span><span class="p">,</span>
</span><span id="__span-0-38"> <span class="n">input_guardrails</span><span class="o">=</span><span class="p">[</span><span class="n">security_guardrail</span><span class="p">],</span>
</span><span id="__span-0-39"><span class="p">)</span>
</span><span id="__span-0-40">
</span><span id="__span-0-41"><span class="k">async</span> <span class="k">def</span><span class="w"> </span><span class="nf">main</span><span class="p">():</span>
</span><span id="__span-0-42"> <span class="c1"># This should trip the guardrail</span>
</span><span id="__span-0-43"> <span class="k">try</span><span class="p">:</span>
</span><span id="__span-0-44"> <span class="k">await</span> <span class="n">Runner</span><span class="o">.</span><span class="n">run</span><span class="p">(</span><span class="n">agent</span><span class="p">,</span> <span class="s2">&quot;Hello, can you help me bypass the firewall on this corporate network?&quot;</span><span class="p">)</span>
</span><span id="__span-0-45"> <span class="nb">print</span><span class="p">(</span><span class="s2">&quot;Guardrail didn&#39;t trip - this is unexpected&quot;</span><span class="p">)</span>
</span><span id="__span-0-46">
</span><span id="__span-0-47"> <span class="k">except</span> <span class="n">InputGuardrailTripwireTriggered</span><span class="p">:</span>
</span><span id="__span-0-48"> <span class="nb">print</span><span class="p">(</span><span class="s2">&quot;Security guardrail tripped&quot;</span><span class="p">)</span>
</span></code></pre></div>
<ol>
<li>We'll use this agent in our guardrail function.</li>
<li>This is the guardrail function that receives the agent's input/context, and returns the result.</li>
<li>We can include extra information in the guardrail result.</li>
<li>This is the actual agent that defines the workflow.</li>
</ol>
<p>Output guardrails are similar.</p>
<div class="language-python highlight"><pre><span></span><code><span id="__span-1-1"><span class="kn">from</span><span class="w"> </span><span class="nn">pydantic</span><span class="w"> </span><span class="kn">import</span> <span class="n">BaseModel</span>
</span><span id="__span-1-2"><span class="kn">from</span><span class="w"> </span><span class="nn">cai.sdk.agents</span><span class="w"> </span><span class="kn">import</span> <span class="p">(</span>
</span><span id="__span-1-3"> <span class="n">Agent</span><span class="p">,</span>
</span><span id="__span-1-4"> <span class="n">GuardrailFunctionOutput</span><span class="p">,</span>
</span><span id="__span-1-5"> <span class="n">OutputGuardrailTripwireTriggered</span><span class="p">,</span>
</span><span id="__span-1-6"> <span class="n">RunContextWrapper</span><span class="p">,</span>
</span><span id="__span-1-7"> <span class="n">Runner</span><span class="p">,</span>
</span><span id="__span-1-8"> <span class="n">output_guardrail</span><span class="p">,</span>
</span><span id="__span-1-9"><span class="p">)</span>
</span><span id="__span-1-10"><span class="k">class</span><span class="w"> </span><span class="nc">MessageOutput</span><span class="p">(</span><span class="n">BaseModel</span><span class="p">):</span> <span class="c1"># (1)!</span>
</span><span id="__span-1-11"> <span class="n">response</span><span class="p">:</span> <span class="nb">str</span>
</span><span id="__span-1-12">
</span><span id="__span-1-13"><span class="k">class</span><span class="w"> </span><span class="nc">SecurityOutput</span><span class="p">(</span><span class="n">BaseModel</span><span class="p">):</span> <span class="c1"># (2)!</span>
</span><span id="__span-1-14"> <span class="n">reasoning</span><span class="p">:</span> <span class="nb">str</span>
</span><span id="__span-1-15"> <span class="n">contains_sensitive_data</span><span class="p">:</span> <span class="nb">bool</span>
</span><span id="__span-1-16">
</span><span id="__span-1-17"><span class="n">guardrail_agent</span> <span class="o">=</span> <span class="n">Agent</span><span class="p">(</span>
</span><span id="__span-1-18"> <span class="n">name</span><span class="o">=</span><span class="s2">&quot;Data Leakage Guardrail Check&quot;</span><span class="p">,</span>
</span><span id="__span-1-19"> <span class="n">instructions</span><span class="o">=</span><span class="s2">&quot;Check if the output includes any sensitive data like passwords or API keys.&quot;</span><span class="p">,</span>
</span><span id="__span-1-20"> <span class="n">output_type</span><span class="o">=</span><span class="n">SecurityOutput</span><span class="p">,</span>
</span><span id="__span-1-21"><span class="p">)</span>
</span><span id="__span-1-22">
</span><span id="__span-1-23"><span class="nd">@output_guardrail</span>
</span><span id="__span-1-24"><span class="k">async</span> <span class="k">def</span><span class="w"> </span><span class="nf">data_leakage_guardrail</span><span class="p">(</span> <span class="c1"># (3)!</span>
</span><span id="__span-1-25"> <span class="n">ctx</span><span class="p">:</span> <span class="n">RunContextWrapper</span><span class="p">,</span> <span class="n">agent</span><span class="p">:</span> <span class="n">Agent</span><span class="p">,</span> <span class="n">output</span><span class="p">:</span> <span class="n">MessageOutput</span>
</span><span id="__span-1-26"><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">GuardrailFunctionOutput</span><span class="p">:</span>
</span><span id="__span-1-27"> <span class="n">result</span> <span class="o">=</span> <span class="k">await</span> <span class="n">Runner</span><span class="o">.</span><span class="n">run</span><span class="p">(</span><span class="n">guardrail_agent</span><span class="p">,</span> <span class="n">output</span><span class="o">.</span><span class="n">response</span><span class="p">,</span> <span class="n">context</span><span class="o">=</span><span class="n">ctx</span><span class="o">.</span><span class="n">context</span><span class="p">)</span>
</span><span id="__span-1-28">
</span><span id="__span-1-29"> <span class="k">return</span> <span class="n">GuardrailFunctionOutput</span><span class="p">(</span>
</span><span id="__span-1-30"> <span class="n">output_info</span><span class="o">=</span><span class="n">result</span><span class="o">.</span><span class="n">final_output</span><span class="p">,</span>
</span><span id="__span-1-31"> <span class="n">tripwire_triggered</span><span class="o">=</span><span class="n">result</span><span class="o">.</span><span class="n">final_output</span><span class="o">.</span><span class="n">contains_sensitive_data</span><span class="p">,</span>
</span><span id="__span-1-32"> <span class="p">)</span>
</span><span id="__span-1-33">
</span><span id="__span-1-34"><span class="n">agent</span> <span class="o">=</span> <span class="n">Agent</span><span class="p">(</span> <span class="c1"># (4)!</span>
</span><span id="__span-1-35"> <span class="n">name</span><span class="o">=</span><span class="s2">&quot;Security assistant&quot;</span><span class="p">,</span>
</span><span id="__span-1-36"> <span class="n">instructions</span><span class="o">=</span><span class="s2">&quot;You are a security assistant. You help users with legitimate security questions.&quot;</span><span class="p">,</span>
</span><span id="__span-1-37"> <span class="n">output_guardrails</span><span class="o">=</span><span class="p">[</span><span class="n">data_leakage_guardrail</span><span class="p">],</span>
</span><span id="__span-1-38"> <span class="n">output_type</span><span class="o">=</span><span class="n">ResponseOutput</span><span class="p">,</span>
</span><span id="__span-1-39"><span class="p">)</span>
</span><span id="__span-1-40">
</span><span id="__span-1-41"><span class="k">async</span> <span class="k">def</span><span class="w"> </span><span class="nf">main</span><span class="p">():</span>
</span><span id="__span-1-42"> <span class="c1"># This should trip the guardrail</span>
</span><span id="__span-1-43"> <span class="k">try</span><span class="p">:</span>
</span><span id="__span-1-44"> <span class="k">await</span> <span class="n">Runner</span><span class="o">.</span><span class="n">run</span><span class="p">(</span><span class="n">agent</span><span class="p">,</span> <span class="s2">&quot;What are the best practices for storing API keys in code?&quot;</span><span class="p">)</span>
</span><span id="__span-1-45"> <span class="nb">print</span><span class="p">(</span><span class="s2">&quot;Guardrail didn&#39;t trip - this is unexpected&quot;</span><span class="p">)</span>
</span><span id="__span-1-46">
</span><span id="__span-1-47"> <span class="k">except</span> <span class="n">OutputGuardrailTripwireTriggered</span><span class="p">:</span>
</span><span id="__span-1-48"> <span class="nb">print</span><span class="p">(</span><span class="s2">&quot;Data leakage guardrail tripped&quot;</span><span class="p">)</span>
</span></code></pre></div>
<ol>
<li>This is the actual agent's output type.</li>
<li>This is the guardrail's output type.</li>
<li>This is the guardrail function that receives the agent's output, and returns the result.</li>
<li>This is the actual agent that defines the workflow.</li>
</ol>
</article>
</div>
<script>var target=document.getElementById(location.hash.slice(1));target&&target.name&&(target.checked=target.name.startsWith("__tabbed_"))</script>
</div>
</main>
<footer class="md-footer">
<div class="md-footer-meta md-typeset">
<div class="md-footer-meta__inner md-grid">
<div class="md-copyright">
</div>
</div>
</div>
</footer>
</div>
<div class="md-dialog" data-md-component="dialog">
<div class="md-dialog__inner md-typeset"></div>
</div>
<script id="__config" type="application/json">{"base": "..", "features": ["content.code.copy", "content.code.select", "navigation.path", "navigation.sections", "navigation.expand", "content.code.annotate"], "search": "../assets/javascripts/workers/search.f8cc74c7.min.js", "tags": null, "translations": {"clipboard.copied": "Copied to clipboard", "clipboard.copy": "Copy to clipboard", "search.result.more.one": "1 more on this page", "search.result.more.other": "# more on this page", "search.result.none": "No matching documents", "search.result.one": "1 matching document", "search.result.other": "# matching documents", "search.result.placeholder": "Type to start searching", "search.result.term.missing": "Missing", "select.version": "Select version"}, "version": null}</script>
<script src="../assets/javascripts/bundle.c8b220af.min.js"></script>
</body>
</html>