Thoughts, stories and ideas.

Why Your LLM Bill Is a Black Box (And How to Fix It)

The invoice from your LLM provider landed last month. $47,000. You knew it was coming because you watched the number climb all month in your provider dashboard. What you don't know is where it went. Was it your customer-facing chat feature? The internal doc summarizer your

LLM Proxy Architecture: The Missing Layer in Your AI Stack

Most teams building AI-powered products have the same architecture: application code that calls LLM provider APIs directly. It works. It's fast to set up. It also quietly creates a set of problems that compound as you scale. A proxy layer between your application and your LLM providers

After the LiteLLM Supply Chain Attack: What Changes

In early 2025, security researchers documented a supply chain attack targeting LiteLLM, one of the most widely used open-source LLM proxy libraries. The attacker group, tracked as TeamPCP, compromised a dependency in the LiteLLM package ecosystem and used it to exfiltrate API keys from applications running the library. The

We Simulated a Runaway Agent and Left It Running Overnight. Here's What the Bill Looked Like.

A runaway agent in a retry loop costs more than most teams expect. Here's the math, why SDK wrappers don't stop it, and how a proxy does.

LLM Proxy vs. SDK Wrappers: Why We Built a Proxy (And What the Latency Numbers Show)

SDK wrappers are the obvious first choice for LLM cost tracking. Here's why they break -- and what the latency benchmarks look like for the proxy alternative.

Why Your AI Bill Has No Attribution (And What That's Costing You)

OpenAI gives you total tokens. They don't tell you which agent drove the spike. Here's why that's becoming a real operational problem -- and what attribution actually requires.

Building an Open-Source LLM Cost Control Plane

Why we chose a proxy over SDK instrumentation, how TimescaleDB makes budget checks fast, and what the three enforcement modes look like in production.