001
Aug 13, 20263 minMembers
The eval harness is the product
If you cannot prove your AI feature got better this week, you are not engineering it — you are decorating it. A working harness, and the failure modes that make most of them lie.
Topic
Production Reliability
Latency budgets, blast radius, graceful degradation — the non-functional requirements that decide whether an AI feature ships.
002
Aug 6, 20261 min
Determinism is a budget, not a property
You cannot make an LLM deterministic. You can decide exactly how much nondeterminism each part of your system is allowed to spend, and enforce it at the boundaries.
Subscribe
New production reliability pieces, by email.
One piece a week on what holds up in production. No digest, no roundup, no course funnel.