Articles
Notes from production.
What we learn building lakehouses and running AI agents on Google Cloud for enterprise teams: cost, reliability and the details that decide both.
DraftPrompt cachingGeminiCost
Prompt caching: stop paying full price for the context you send every time
Most agent and RAG prompts repeat the same long prefix on every call. Context caching on Google Cloud lets you pay for it once. How implicit and explicit caching work, and how to design prompts that hit the cache.
DraftTokenomicsAgentsCost
Tokenomics: the unit economics of AI agents
Token prices are the easy part. What decides whether an agent is affordable at enterprise scale is how many tokens each task really uses. A practical way to estimate, measure and reduce cost per task.