A new engineering guide warns that multi-agent systems require early architectural decisions on observability, access control, trust boundaries, and failure models to avoid costly refactoring. The gui…
Kong Inc. introduced the Kong AI Gateway, a runtime for managing LLM traffic that standardizes interfaces across providers, centralizes credentials, and enforces token-based rate limiting, PII sanitiz…
AI agent context management controls the information an AI model accesses at any moment, distinguishing between retrieving (read) and mutating (write) operations to ensure accurate decisions and secur…
Kong Inc., an API platform provider, reports that AI adoption in enterprises remains low, with the highest vertical penetration at 17% and software at 8%, but urges companies to implement governance n…
Kong Inc. will host its Kong Partner Summit 2026 in Los Angeles this September, preceding the API + AI Summit, to focus on moving organizations from AI experimentation to production-ready, enterprise-…
The API + AI Summit 2026 will feature a session titled 'Stop Patching. Start Building: The Kong Context Mesh Stack,' which argues that existing infrastructure—compute, event streaming, data stores, an…
Kong Inc. announced that submissions for the 2026 Kong Innovator Awards are now open, honoring customers who use Kong to solve complex problems with innovative approaches. Last year's winners included…
A new analysis argues that traditional integration platform as a service (iPaaS) architectures are fundamentally incompatible with the real-time, adaptive demands of agentic AI, citing three critical …
Kong Inc. announced the Context Mesh Stack, an AI Gateway that sits between agents and LLMs to enforce PII masking, confidence thresholds, semantic caching, prompt injection detection, and cost attrib…
AI agents fail not because of model quality but because of stale data, brittle integration, and latency, according to a technical analysis. Batch-oriented enterprise pipelines deliver outdated informa…
Mooter's research finds that enterprises adopting AI agents need a dedicated integration layer, as agents require governed access to systems for actions like querying databases or triggering workflows…
Kafka event streams need an event gateway to address four key issues: exposing internal broker addresses externally creates security and operational risks, organizations often have multiple Kafka clus…
Portkey.ai outlines three AI traffic patterns—App-to-LLM, Agent-to-Agent, and Model Context Protocol—that require a unified proxy gateway for authentication, rate limiting, guardrails, and audit trail…
Kong and ModelOp have partnered to deliver zero-trust security for the agentic enterprise, integrating Kong's AI Gateway with ModelOp's Enterprise AI Command Center to enforce governance policies on A…
Kong Inc. announced Kong AI Gateway 2.0, a standalone product with its own runtime, control plane, admin API, and version number, decoupled from Kong API Gateway to support the faster release cadence …
Kong's AI Gateway operates at the infrastructure layer, enforcing policies defined by AI governance platforms, which Gartner categorizes separately in its Magic Quadrant. The distinction highlights th…
Multiple critical vulnerabilities in Langflow and Dify AI agent platforms have enabled remote code execution and data exposure, with one Langflow flaw exploited within 20 hours of disclosure. Security…
Shadow AI detection identifies unsanctioned AI tools and models deployed without security approval, often by inspecting traffic at an AI gateway. Kong research found 54% of enterprises with governance…
Enterprise-grade MCP access control is now available, with EMA (Enterprise MCP Authentication) enabling secure token exchange between clients and servers. The system addresses gaps where clients or se…
An AI gateway is a dedicated infrastructure layer that manages traffic between applications and LLM providers, handling routing, failover, rate limiting, and policy enforcement. It differs from a regu…