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.