Kong Inc., a pioneer in cloud API technologies, has announced the release of the latest version of Kong AI Gateway, designed to enhance AI security and governance. This new update introduces essential guardrails for making Generative AI (GenAI) and Agentic AI production-ready, addressing critical challenges in AI implementation. Key enhancements include automated Retrieval-Augmented Generation (RAG) pipelines to mitigate Large Language Model (LLM) hallucinations and a Personally Identifiable Information (PII) sanitization plugin, which safeguards sensitive data across 12 languages and major AI platforms.
“As artificial intelligence continues to evolve, organizations must adopt robust AI infrastructure to harness its full potential,” said Marco Palladino, CTO and Co-Founder, Kong Inc. “With this latest version of AI Gateway, we’re equipping our customers with the tools necessary to implement Agentic AI securely and effectively, ensuring seamless integration without compromising user experience. Moreover, we’re helping solve some of the biggest challenges with LLMs, such as cutting down on hallucinations and improving data security and governance.”
AI Gateway Now Integrated with Kong Konnect
Kong AI Gateway 3.10 is now part of Kong Konnect, an API lifecycle platform built to drive API-driven innovation at scale. High-quality, secure, and resilient APIs are essential for seamless digital experiences, but managing them effectively remains a challenge. Konnect simplifies API operations by providing built-in governance, automation, and monetization capabilities, accelerating innovation and enabling the creation of AI-driven applications with enhanced security and efficiency.
Also Read: Amazon simplifies access to Amazon Nova Gen AI models
Key Features of Kong AI Gateway 3.10
AI RAG Injector:
- Reduces LLM Hallucinations: The automated RAG pipelines help address the issue of AI-generated inaccuracies by dynamically querying a vector database and injecting relevant data into prompts, ensuring responses are backed by verified knowledge sources.
- Enhances Security and Compliance: By offloading RAG pipeline responsibilities to the AI Gateway, organizations can place the vector database behind a secure layer, strengthening overall data security and governance.
- Boosts Developer Productivity: Traditionally, RAG pipelines require extensive manual effort. AI Gateway 3.10 simplifies integration with a low-code/no-code approach, enabling developers to generate embeddings, retrieve relevant data, and append it to requests with minimal effort.
Automatic PII Sanitization:
- Strengthens Data Protection: This feature automates the sanitization of personal data, passwords, and over 20 PII categories, ensuring compliance across multiple languages and AI platforms. Platform owners can enforce global sanitization policies, eliminating the need for developers to manually code protections into each application.
- Optimizes User Experience: Unlike other solutions that merely redact or replace sensitive data with tokens, Kong AI Gateway 3.10 offers an option to reinstate sanitized data into responses based on platform-defined configurations. This ensures end users receive accurate, personalized information without compromising security.
With these advancements, Kong Inc. continues to lead the way in AI security and governance, empowering businesses to deploy AI-driven solutions with confidence and efficiency.