Sign in Subscribe

ai guardrails

Prompt Injection Attacks in LLMs: What Are They and How to Prevent Them

In February 2023, a Stanford student exposed Bing Chat’s confidential system prompt through a simple text input, revealing the chatbot’s internal guidelines and behavioral constraints. It was one of the first prompt injection attacks highlighting a critical security loophole in Large Language Models (LLMs) – AI models powering everything

Portkey's AI Guardrails

Prompt Security and Guardrails: How to Ensure Safe Outputs

Prompt security is an emerging and essential field within AI development making sure that AI-generated responses are safe, accurate, and aligned with the intended purpose. When prompts are not secured, the resulting outputs can unintentionally generate or amplify misinformation. Compliance risks are also a major concern. Enterprises deploying AI systems

Portkey x Pillar - Enterprise-grade Security for LLMs in Production

Portkey x Pillar - Enterprise-grade Security for LLMs in Production

Bringing Pillar's AI guardrails onboard Portkey's open source Gateway!

Open Sourcing Guardrails on the Gateway Framework

We are solving the *biggest missing component* in taking AI apps to prod → Now, enforce LLM behavior and route requests with precision, in one go.

Portkey & Patronus - Bringing Responsible LLMs in Production

Portkey & Patronus - Bringing Responsible LLMs in Production

Patronus AI's suite of evaluators are now available on the Portkey Gateway.