Tag: observability
All the articles with the tag "observability".
Your Cache Hit Rate Is Not Your Token Savings
Published: at 06:00 AMMeasure uncached input, cache writes, cache reads and output separately. Request hit rate cannot tell you what a long-context workload costs.
The Missing Layer: Why AI Conversations Need Structure
Published: at 10:00 AMAI collapsed the cost of writing code. It didn't touch the cost of understanding it. What if we could make AI sessions as debuggable as the code they produce?