Topic
5 articles on Observability, written from production systems rather than documentation.
Prompts, traces, embeddings and evaluation sets all quietly become copies of user data, and most of them were never on anybody's data map.
Agents rarely crash. They loop, they stop early, and they confidently do the wrong thing, which is why ordinary error handling never catches any of it.
People are the only judges who catch what nobody thought to check for. Spending that attention on random samples wastes most of it.
Grading output with another model scales in a way humans cannot. It also has biases of its own, and a judge nobody validated is just a number.
Request logs tell you a call succeeded. For a model-driven system the useful record is the whole chain, because the mistake is rarely in the last step.
Whether it needs designing from scratch or rescuing from its own success, tell me what you’re building and I’ll tell you how I’d architect it.
Open to remote and hybrid work worldwide