IceGate

LLM observability is the practice of recording what an LLM application actually did on every request - the prompt, the response, the tool calls, the tokens - so any single run can be reconstructed afterwards. Technically it's distributed tracing. ... [More] Practically it's a different job, because the payload rather than the timing is the signal. Here's what it records, how it differs from monitoring and evals, and what it changes about your data and your bill. [Less]

The OpenTelemetry GenAI semantic conventions let you trace an LLM agent the same way you trace the rest of your stack. A hands-on guide: zero-code auto-instrumentation, manual agent and tool spans, token usage and cost, opt-in prompt capture ... [More] , grouping multi-turn conversations across traces, and where to send the data. None of it ties you to a vendor, so the data stays yours. [Less]

LLM monitoring and observability is billed at one premium AI rate, but agentic apps emit mixed traces: heavy LLM spans interleaved with just as many ordinary ones - HTTP, DB, queues, infra. So your observability cost grows with the number of agents ... [More] and tool calls - with your success, not with the value of the data. Here's the fix: price AI data as AI data, and everything else as plain telemetry. [Less]

Yes - you can run observability ingestion on S3 alone, with no stateful layer to operate: no Kafka, no local disks, no coordination service. We replaced an Apache Kafka + Flink + OTel pipeline (~$700–800/month at 10 MB/s) with one engine where the ... [More] data, the WAL, and the Apache Iceberg catalog all live in S3, with durability backed by S3. Here's how it works. [Less]