Fortifying Your AI Stack: Palo Alto Networks Prisma AIRS Now on Portkey

We're excited to announce the integration of Palo Alto Networks Prisma AIRS with Portkey, bringing together industry-leading AI guardrails with comprehensive observability and intelligent routing capabilities.

As organizations increasingly deploy AI systems across their operations, enabling these systems to operate safely, effectively, and transparently becomes paramount.

This partnership combines Prisma AIRS' powerful guardrails with Portkey's robust gateway and observability to deliver a complete solution for responsible AI deployment.

What is Prisma AIRS?

Palo Alto Networks Prisma AIRS is a purpose-built, centralized security platform that protects your entire AI ecosystem. It provides comprehensive protection for AI applications, models, data, and agents through real-time threat detection and inline security enforcement across all OSI layers (1-7).

Prisma AIRS offers two protection modes:

• Network Intercept: Real-time, inline protection for cloud network architectures
• API Intercept: Security-as-Code embedded directly into your applications

What Prisma AIRS protects against

Prisma AIRS provides multi-layered protection against various AI-specific threats:

Security Threats Detected

1. Malicious URL Detection: Detects and blocks malicious URLs in your LLM requests/responses
2. Prompt Injections: Prevents attempts to manipulate AI behavior through malicious prompts
3. Sensitive Data Leakage: Blocks PII, secrets, and confidential information from being exposed
4. Insecure Outputs: Filters responses containing malware, malicious URLs, or harmful content
5. Model DoS Attacks: Protects against attempts to overwhelm or disable AI models
6. Jailbreak Attempts: Identifies and prevents attempts to bypass AI safety mechanisms
7. Toxic Content: Filters harmful, offensive, or inappropriate content

Enhanced security with complete visibility

The integration streamlines the process of securing AI applications by embedding security directly into the AI gateway. Users can add the Prisma AIRS guardrail through Portkey’s native Guardrails module with a simple configuration. This one-time setup at the gateway level reduces operational complexity and removes the need to write security code for each individual application.

This integration allows you to:

1. Secure AI interactions: Apply Prisma AIRS' comprehensive security controls to all AI traffic flowing through Portkey
2. Monitor security events: Gain visibility into security-related events alongside performance and usage metrics - you can see the verdict and any actions taken directly in your Portkey logs
3. Apply intelligent routing decisions: Route AI traffic based on both security requirements and performance considerations
4. Centralize management: Configure and manage security, observability, and routing through a unified interface
   

The combined solution strengthens your AI security posture while providing the tools to optimize performance, control costs, and ensure compliance.

Leaders from both organizations highlighted the collaboration as a vital way to enable secure innovation.

"By embedding AI Runtime Security directly into the AI gateway, we are simplifying security operations. Enforcement of AI threats can be implemented without making any changes to application code."

- Jaimin Patel, Sr. Director of Product for Prisma AIRS at Palo Alto Networks

Rohit Agarwal, CEO of Portkey, echoes this sentiment:

"This seamless integration means our users can now leverage Prisma AIRS's powerful threat detection capabilities directly within their existing Portkey workflows, offering unparalleled protection... It's about enabling our users to innovate faster and more securely."

Secure your AI apps today

By uniting Portkey’s advanced AI gateway capabilities with the comprehensive security of Prisma AIRS, developers and security teams can build, deploy and protect innovative AI solutions with confidence.

To get started, take a look at our detailed documentation or book a detailed walkthrough.