Linh commit notebook for Building Secure Agentic AI Systems with Safe…

[linhkid]

…ty Guardrails (correct CLA)

Defending Against Jailbreaks using Google ADK with LLM-as-a-Judge and Model Armor

In this notebook, you'll learn how to build production-ready Agentic AI systems with comprehensive safety guardrails using Google's Agent Development Kit (ADK), Gemini and Cloud services.

[review-notebook-app]

Check out this pull request on 

See visual diffs & provide feedback on Jupyter Notebooks.

---

Powered by ReviewNB

[gemini-code-assist]

Summary of Changes

Hello @linhkid, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request integrates a new, extensive Jupyter notebook into the examples, focusing on the critical aspect of AI safety within Agentic AI systems. The notebook provides practical guidance on implementing comprehensive safety guardrails using Google's Agent Development Kit (ADK), Gemini, and Google Cloud services. It thoroughly covers various AI safety threats, such as jailbreaks and prompt injections, and showcases two distinct defense strategies: an LLM-as-a-Judge plugin for dynamic content evaluation and Google Cloud Model Armor for scalable, pre-trained safety filtering. A key emphasis is placed on preventing session poisoning, ensuring that malicious inputs do not compromise the agent's memory or future responses.

Highlights

• New AI Safety Notebook: Introduces a detailed Jupyter notebook on building secure Agentic AI systems with comprehensive safety guardrails using Google ADK, Gemini, and Cloud services.
• Dual Safety Approaches: Demonstrates two distinct methods for implementing AI safety: an LLM-as-a-Judge plugin for flexible, context-aware filtering and Google Cloud Model Armor for robust, enterprise-grade protection.
• Session Poisoning Prevention: Highlights techniques to prevent malicious content from being stored in conversation history, effectively safeguarding against session poisoning attacks.
• Updated Examples Index: The examples/README.md file has been updated to include the new notebook in the list of available examples, along with minor table formatting adjustments.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request adds a new notebook demonstrating how to build secure AI agents with safety guardrails, and updates the main README to include it. The notebook is comprehensive and well-structured. My review focuses on ensuring adherence to the repository's style guide, fixing a few broken links, and addressing some hardcoded values that should be placeholders. Overall, this is a great addition to the cookbook.

[linhkid]

I have resolved all the comments during the code review. Please let me know if anything else is needed to be done on my end