Blog
Cloud and AI cost, managed like code. One post a week, written for engineers and the people who pay the bill.
- Implement AWS cost recommendations as pull requests
AWS cost recommendations stall between the finding and the change. Turning each saving into a pull request you approve, then measuring it, fixes that.
- Five LLM cost levers to check before you switch providers
Before moving to a cheaper AI provider, check five levers that reduce LLM costs where you are: model routing, caching, batch, output limits and context.