Blog

My wife and I are really into cooking. A few years ago, after an outing with some food bloggers, she came home with some spices in a bag with a hand-written label that looked like “threbe”. We thought it was some kind of wild oregano from Greece, a...

Feb 25, 2025

It’s no secret that Generative AI is reshaping every facet of our world today. To put this into perspective - some of the largest organizations that we’re speaking with have 900 ACTIVE generative AI projects right now! Securing these applications has...

Feb 18, 2025

Leading companies are rapidly developing AI applications by combining enterprise data with large language models (LLMs). However, this explosion in AI development and adoption is also introducing critical security risks like prompt injection, excessi...

Feb 12, 2025

Pangea Prompt Guard Now in Beta We’re excited to announce that Prompt Guard is now in Beta! – Designed to address the most pressing AI security challenges. Prompt Guard identifies and stops direct and indirect prompt injection attacks, a growing thre...

Feb 6, 2025

As organizations rush to build AI applications that integrate enterprise and customer data with large language models (LLMs), it's crucial to understand and mitigate the security risks that come with this new technology. In a recent webinar hosted by...

Feb 6, 2025

Report: Gartner® 2024 Emerging Tech - Secure Generative Communication for LLMs and AI Agents Building and deploying AI-driven applications comes with risks for engineering and security leaders. “Deploying security services across multiple points in t...

Jan 22, 2025

Effective logging in AI applications is not just a technical best practice—it’s a critical requirement for operational success, security, and compliance. As AI continues to permeate industries, the need for robust logging mechanisms has grown signifi...

Jan 17, 2025

Generative AI is revolutionizing industries, creating unprecedented opportunities—and equally unprecedented risks. Whether you’re a security leader, engineering leader, or developer, you’ve likely encountered new challenges in protecting sensitive da...

Jan 14, 2025

Designing authorization is fundamentally a challenge. Not only do you have to understand your problem and domain fully but you also need to understand the limits of your tools. If you get either wrong - or maybe just not as correct as you should - yo...

Jan 7, 2025

Intro: Analogies Network security back in the 1990’s through the mid-2010’s was a very exciting time where user connectivity rapidly evolved, creating tons of vulnerabilities and exploit techniques that all happened over the network and internet. Thi...

Jan 7, 2025

As we’ve worked with customers evaluating Large Language Models (LLMs) for their organizations, the recurring theme was authorization. In too many of these systems, data in the form of pdfs, Google docs, and more are added to give better, more refine...

Jan 7, 2025

New Products: Securing AI Applications with AI & Prompt Guard With our recent launch of AI Guard & Prompt Guard Pangea now offers the broadest set of AI Security Guardrails in the industry. AI Guard and Prompt Guard are two cutting-edge solutions des...

Dec 9, 2024

I’ve spent many weeks on the road this past quarter speaking to teams all over the country about their AI product initiatives and I am struck by a particular challenge I’ve heard repeatedly expressed: when developing retrieval-augmented generation (R...

Dec 5, 2024

As companies increasingly turn to AI-driven systems to support customer interactions through systems like chatbots and streamline operations, Retrieval-Augmented Generation (RAG) has become a popular framework for enhancing large language models (LLM...

Oct 31, 2024

When we look at the current state of generative AI, we think of products like ChatGPT, Google Gemini, Claude, and similar. Those are all publicly available tools trained on public data and useful for general topics for a general audience. But if we e...

Oct 30, 2024

It’s been a few months since Microsoft Build 2024 where one of the highlights was the launch of the Pangea extension for GitHub Copilot. Pangea was able to interface with Copilot Chat, bringing security into the development environment. Developers ...

Oct 29, 2024

I have spent much of the past two months on the road speaking with organizations of all industries about their AI application initiatives and I am struck both by their techno optimism and by the depth of their security concerns. The pace of innovatio...

Oct 28, 2024

Pangea is proud to announce the general availability of Secure Share. Secure Share is a set of APIs that make it easy to add secure file sharing to your application. Apps often need to send and receive sensitive files - such as a mortgage applicatio...

Oct 16, 2024