Jjasmineparkinjas-blogs.hashnode.dev·2d ago · 6 min readWhat wakes you at 2am when an enterprise operator deploys your agent Month one of our enterprise rollout: three 3am pages. None of them were code bugs. None of them were model quality issues. All of them were operational surprises we had not accounted for before the ha00
Jjasmineparkinjas-blogs.hashnode.dev·3d ago · 5 min readThe Langfuse migration that cost us a sprint: how I now budget LLM observability We moved off our first tracer in month eight. The migration took one engineer the better part of a sprint, because the trace data lived in a schema we did not own. Nobody costed that line item on day 00
Jjasmineparkinjas-blogs.hashnode.dev·Jun 25 · 21 min readThe gateway tax : 6 OpenAI-compatible gatewaysOn March 14, 2026, our LLM bill came in at \(9,140 for the month, up from about \)5,200, and I could not tell you which team spent it. The gateway in front of every provider emitted one cost line and 00
Jjasmineparkinjas-blogs.hashnode.dev·Jun 19 · 6 min readLangfuse alternatives: 6 LLM observability tools, sorted by the thing that bites you in month eight TL;DR I went looking for Langfuse alternatives after living with a proprietary tracer for eight months and then paying to migrate off it. I compared six options: Helicone Arize Phoenix LangSmith B00
Jjasmineparkinjas-blogs.hashnode.dev·Jun 16 · 3 min readWe put a cost SLO on our LLM features. It is the number that finally made eng care about token spend. TL;DR: Our LLM bill was a single number going up, and "spend rose 18%" is not something an engineer can act on. We gave each feature a cost SLO, a target cost per successful outcome with a monthly err00
