Article · 4 min
How to cut LLM cost with prompt caching
How a stable prompt prefix turns repeat agent calls into cache hits, what breaks the cache, and how to measure it.
Writing on Cost
What worked, what it cost and what I'd change, from building data platforms and AI agents.
Posts
Article · 3 min
How to cut compute and storage use on a data platform
Where the money went on a busy data platform, and the fixes that brought compute and storage usage down.
Article · 2 min
How to allocate AWS cost for data platforms
Splitting a shared cloud bill across teams when the billing data and the usage data share no key. Then turning usage into an estimate.
Nothing here yet.