In a move designed to bolster the security of rapidly expanding AI ecosystems, we’ve teamed up with Portkey, AI gateway provider, to integrate the comprehensive Prisma AIRS® security platform directly into Portkey's AI gateway. By implementing security guardrails at the gateway level, developers will have a streamlined method to protect their applications from an array of AI-specific threats, such as prompt injections and sensitive data leakage.
Combine Operational Ease with Robust AI Security
It’s an important collaboration, which brings together two powerful platforms. Portkey provides a robust AI gateway that streamlines the development and management of AI applications. Developers get observability, reliability, as well as cost management through a universal API that supports over 1,600 large language models (LLMs). This allows development teams to focus on innovation rather than operational complexity.
Complementing this, Palo Alto Networks Prisma AIRS is the most comprehensive AI security platform designed to protect the entire AI ecosystem. It delivers real-time, AI-powered security to safeguard applications, models and data from a wide range of threats.
Simplify Your Security with a One-Time Setup
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. Teams can then monitor their AI security posture through both the Portkey logs and the Prisma AIRS dashboard.
Protect Your Applications from Critical AI Threats
By integrating Prisma AIRS, Portkey users gain comprehensive protection against a variety of vulnerabilities unique to AI systems. The solution actively blocks malicious prompts designed to manipulate AI behavior and prevents the accidental leakage of personally identifiable information (PII) and secrets, including other confidential data. It also stops models from generating insecure outputs containing malware, malicious URLs or toxic content. The guardrails defend against unbounded consumption attacks that could overwhelm models and check LLM responses for contextual grounding to prevent hallucinations and inaccuracies.
Accelerate Your AI Journey with Industry Expert Confidence
Leaders from both organizations highlighted the collaboration as a vital way to enable secure innovation.
Jaimin Patel, Sr. Director of Product for Prisma AIRS at Palo Alto Networks says:
"By embedding AI Runtime Security directly into the AI gateway, we are simplifying security operations. Guaranteed enforcement of AI threats can be implemented without making any changes to application code."
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."
Activate Industry-Leading Protection for Your AI Today
This integration marks a significant step forward in building trustworthy generative AI applications. 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, look at the integration reference and API documentation for Prisma AIRS. See what Prisma AIRS can do for you by requesting a demo.