One message, dozens of calls: how we measured and cut agent-chat spend
A chat message is not one request — it is a loop of model calls. How we attributed LiteLLM spend, saw the whole proxy in Grafana, and cut tokens without breaking the agent.
Resizes journal · 2 articles
engineering
Articles about engineering.
Stop paying $0.40 per secret: cut AWS Secrets Manager cost and run secrets more efficiently
What Secrets Manager really costs at 50, 500, and 5,000 secrets — and how we help organisations move to a portable, cheaper operating model with 1Password and External Secrets.