Capstone 11 — LLM Observability & Eval Dashboard
Langfuse went open-core. Arize Phoenix published the 2026 GenAI semconv mappings. Helicone and Braintrust both doubled down on per-user cost attribution. Traceloop's OpenLLMetry became the de-facto SDK instrumentation. The production shape is ClickHouse for traces, Postgres for metadata, Next.js for UI, and a small army of eval jobs (DeepEval, RAGAS, LLM-judge) running over sampled traces. Build one self-hosted, ingest from at least four SDK families, and demonstrate catching an injected regression in under five minutes. Phases exercised: P11 · P13 · P17 · P18 Every AI team running production traffic in 2026 keeps an observability plane alongside the model. Cost attribution. Hallucination detection. Drift monitoring. Jailbreak signal. SLO dashboards. PII leak alerts. The open-source references — Langfuse, Phoenix, OpenLLMetry — converged on OpenTelemetry GenAI semantic conventions as the ingest schema. You can now instrument OpenAI, Anthropic, Google, LangChain, LlamaIndex, and vLLM with one SDK and ship compatible spans. You will build a self-hosted dashboard that ingests from at least four SDK families, runs a small set of eval jobs over sampled traces, detects drift, and alerts. The measurement bar: given a deliberately injected regression (a prompt that starts producing PII), the dashboard catches it and fires an alert in under five minutes. Ingest is OTLP HTTP. The SDK produces GenAI-semconv spans: genai.system, genai.request.model, genai.usage.inputtokens, genai.response.id, llm.prompts, llm.completions. Spans land in…
Capstone 11 — LLM Observability & Eval Dashboard: Langfuse went open-core. Arize Phoenix published the 2026 GenAI semconv mappings. Helicone and Braintrust…
This free lesson is part of the AI Engineering from Scratch curriculum. Read the full explanation, run the lesson code, and verify the result in the interactive reader or from the repository source.
Browse the complete course catalog or open this lesson on GitHub.