Tetrate Blog

Expert knowledge, news, deep-dives straight to your inbox

Envoy

Announcing Built On Envoy: Making Envoy Extensions Accessible to Everyone

How to solve LLM provider lock-in, outages, and cost overruns with an AI gateway

Agent Router Enterprise

Jun 9, 2026

How to solve LLM provider lock-in, outages, and cost overruns with an AI gateway

HTTP Bomb (CVE-2026-47774): What Every Envoy User Needs to Know

Agent Router Enterprise

Jun 8, 2026

HTTP Bomb (CVE-2026-47774): What Every Envoy User Needs to Know

The HTTP Bomb (CVE-2026-47774) is a high-severity HTTP/2 denial-of-service flaw in Envoy proxy. A single connection can exhaust 32 GB of memory in ~10 seconds. Here is how it works, who is affected, the patched Envoy versions, and how to mitigate it.

Parameter-Level Authorization for AI Agents: Enforcing Policy on Live MCP Tool Calls

Agent Router Enterprise

Jun 3, 2026

Parameter-Level Authorization for AI Agents: Enforcing Policy on Live MCP Tool Calls

Tetrate Agent Router Enterprise and Ory enforce dynamic, parameter-level authorization on live MCP tool calls, with step-up approval for high-risk agent actions.

Stop Asking People to Tag Their AI Spend

Agent Router Enterprise

May 19, 2026

Stop Asking People to Tag Their AI Spend

About half our AI spend last week was on API keys with no team tag, no workload tag, no owner. That's not a discipline problem, it's a product problem — and the fix isn't a better tagging UI.

Is Your AI Spend Producing Anything? A Manager's Guide

Agent Router Enterprise

May 19, 2026

Is Your AI Spend Producing Anything? A Manager's Guide

Your AI budget doubled. Someone is going to ask you whether it's producing anything. Most managers don't have a great answer. Here are the two levers you actually have, and a three-question Monday-morning diagnostic.

What is an AI gateway, and why every LLM team needs one

Agent Router Enterprise

Apr 23, 2026

What is an AI gateway, and why every LLM team needs one

An AI Gateway handles routing to one or more AI models, fallback, authentication, cost control, and observability.

SR 11-7 Just Wrote Itself Out of the GenAI Conversation

Agent Router Enterprise

Apr 22, 2026

SR 11-7 Just Wrote Itself Out of the GenAI Conversation

The April 17, 2026 interagency MRM rewrite explicitly carves generative and agentic AI out of scope. That's not a retreat — it's an RFI window, and it's the firms with deployed controls that will shape what comes next.

Agent Security: What NIST Wants You to Think About Before Your Agent Calls a Tool

Agent Router Enterprise

Apr 21, 2026

Agent Security: What NIST Wants You to Think About Before Your Agent Calls a Tool

Your agent has AWS credentials. It can execute cloud CLI commands. NIST has opinions about this. Here's what tool-calling security looks like in practice.

Making Agents Reliable: Auto-Save, Stable IDs, and the Context Window Problem

Agent Router Enterprise

Apr 15, 2026

Making Agents Reliable: Auto-Save, Stable IDs, and the Context Window Problem

When your agent crashes at tool call 142 out of 150, you'd better hope the first 141 findings aren't lost. Here are the patterns that made our cost agents production-ready.

Announcing Built On Envoy: Making Envoy Extensions Accessible to Everyone

Tetrate Blog

Announcing Built On Envoy: Making Envoy Extensions Accessible to Everyone

How to solve LLM provider lock-in, outages, and cost overruns with an AI gateway

HTTP Bomb (CVE-2026-47774): What Every Envoy User Needs to Know

Parameter-Level Authorization for AI Agents: Enforcing Policy on Live MCP Tool Calls

Stop Asking People to Tag Their AI Spend

Is Your AI Spend Producing Anything? A Manager's Guide

What is an AI gateway, and why every LLM team needs one

SR 11-7 Just Wrote Itself Out of the GenAI Conversation

Agent Security: What NIST Wants You to Think About Before Your Agent Calls a Tool

Making Agents Reliable: Auto-Save, Stable IDs, and the Context Window Problem

Ready to enhance your network with more intelligence?

Ready to enhance your
network
with more
intelligence?