As organizations race to deploy AI-powered applications, keeping everything secure is a top priority. Developers need to move fast, but security teams need to ensure that every AI interaction is safe, compliant and protected from threats. The big question: how do you secure the hundreds or even thousands of models your teams are using without complex, custom engineering for each one?
At Palo Alto Networks, our goal is to deliver security that is both simple and robust. That’s why we’re thrilled to announce our integration with TrueFoundry, bringing the power of Prisma® AIRS™ to the TrueFoundry AI Gateway. This partnership empowers your organization to enforce consistent, enterprise-grade security across all your AI models and applications from a single, centralized platform, helping to ensure your AI initiatives are protected.
The Power of the TrueFoundry AI Gateway
The TrueFoundry AI Gateway is a powerful way for developers and platform teams to manage, monitor and scale their AI applications. It brings together unified access to hundreds of large language models (LLMs), advanced observability and smart routing all in one place. As AI adoption scales, so does the need for strong, centralized security that keeps up without slowing developers down.
As AI adoption accelerates, the real challenge isn’t accessing models; it’s managing the complexity that follows. Multiple providers, evolving APIs and strict compliance needs can quickly slow teams down. The TrueFoundry AI Gateway brings order to this chaos, serving as the command center for enterprise AI. It unifies access, enforces security, and delivers full visibility across every model and environment, empowering organizations to innovate at scale with confidence and control.
Prisma AIRS: World-Class AI Security
Prisma AIRS protects your AI applications and agents in real time by acting as a secure layer between your applications and AI models. It can detect prompt injection attempts on the spot, preventing attackers from manipulating your models to reveal sensitive information or bypass safety controls.
Prisma AIRS also helps prevent data leaks, thanks to built-in data loss prevention (DLP) that flags and blocks any accidental exposure of confidential information. Furthermore, it protects against the entire spectrum of input and output risks: it instantly stops prompt injection attacks attempting to manipulate the model, blocks toxic content from being generated and defends against harmful outputs, like malicious code or inappropriate links, using Advanced URL Filtering before they ever reach your users. And to keep things simple, all your scan logs, alerts and verdicts.
Better Together: A Seamless Integration for Robust Security
The integration of Prisma AIRS and the TrueFoundry AI Gateway simplifies and strengthens your AI security. This combination makes it easier than ever to bake security right into your AI workflow, guaranteeing your system is protected from the moment of deployment.
With this integrated solution, you get a streamlined experience that makes securing your AI models simple and consistent. Instead of juggling different SDKs or scattered code changes, you can apply Prisma AIRS security to any model connected through the TrueFoundry AI Gateway, all with a single integration.
The TrueFoundry AI Gateway automatically listens to Prisma AIRS verdicts and enforces them every time, whether that means blocking a malicious prompt or redacting sensitive data. You can configure Prisma AIRS as a guardrail directly within the TrueFoundry dashboard, giving you centralized control over security policies across different teams, models and environments. For full visibility, Prisma AIRS threat logs are combined with TrueFoundry’s detailed request tracking to provide a complete audit trail, making compliance and incident response much easier.
How the Prisma AIRS and TrueFoundry Integration Works
Prisma AIRS and TrueFoundry Integration
Prisma AIRS and the TrueFoundry AI Gateway work together to simplify and enhance security operations.
How Layered Security Works
The integration simplifies and enhances your security operations by introducing a layered security approach.
1. When your application sends a request, it first passes through the TrueFoundry AI Gateway.
2. The AI Gateway immediately forwards the request to Prisma AIRS, which scans the input for prompt injection and other risks.
3. If the scan returns an "allow" verdict, the request proceeds safely to the AI model. If it returns a "block" verdict, the request is halted, and a safe fall back response is sent instead.
4. Optionally, after the AI model generates a response, the AI Gateway can send this output back to Prisma AIRS for a final scan, ensuring the model's response is also secure before it reaches the application.
As you can see, this layered security approach helps organizations safely scale AI adoption while maintaining strong control over potential threats.
Configuration is just as easy. Simply add Prisma AIRS as a guardrail in your TrueFoundry account, enter your API key and profile name, and you're ready to go.
Get Started with Enterprise-Grade AI Security
AI security does not need to slow you down. With Prisma AIRS integrated into TrueFoundry AI Gateway, you can move quickly without compromising safety. It’s world-class protection that is easy to set up, more like flipping a switch than a complex engineering project.
To learn more, visit our developer documentation and the Prisma AIRS & TrueFoundry integration reference to see how easy it is to secure your AI applications.
Ready to get started? Contact us to see a demo and get a free trial of Prisma AIRS.