LLM Observability at the Gateway: What to Measure, and Where
A guide to LLM observability at the gateway, covering the signals to instrument and how to export them to Prometheus, OpenTelemetry or Datadog.
Latest
Remote MCP Servers: Connecting and Securing SaaS Servers Through One Gateway
TL;DR
* Remote MCP servers are SaaS-hosted Model Context Protocol servers that AI clients reach over HTTP or Server-Sent Events, instead of spawning them as local processes over STDIO.
* Wiring every team to every remote MCP server directly produces credential sprawl, no per-team access control, no audit
Shadow AI Risks: 7 Exposure Categories and the Control for Each (2026)
A breakdown of seven shadow AI exposure categories, the control that closes each one, and how to roll them out fleet-wide through MDM.
AI Governance Strategy for Platform Engineering Teams
A guide to designing an AI governance strategy that fits an internal developer platform, from virtual keys and budgets to MCP tool governance.
How to Govern AI Coding Agents at Scale
TL;DR
* Gartner predicts 90% of enterprise software engineers will use AI code assistants by 2028, up from less than 14% in early 2024, and much of that traffic can leave developer laptops outside any policy layer.
* Governing AI coding agents at scale takes two layers: an AI gateway that
LLM Access Control for Enterprise AI in 2026
TL;DR
* Enterprise LLM access control governs which users, teams, and applications can reach which models, tools, and data across an entire AI footprint, at a scale where shared API keys stop working.
* Five building blocks carry it: federated identity, fine-grained authorization, row-level data scoping, cost governance, and
What Are AI Guardrails? Ensuring Trust and Safety in AI
An explanation of what AI guardrails are, the main types, how they work, and how to implement them consistently at the gateway.