@mlflow

mlflow-onboarding branches users into two paths (genai or traditional ml) based on detected imports and explicit questioning, then guides them to relevant quickstart tutorials.

analyzing-mlflow-trace covers single trace inspection to debug mlflow executions. describes trace structure (spans, operations, timing) and one cli command to fetch traces safely to file, lacking systematic analysis procedure.

searching-mlflow-docs retrieves mlflow documentation by fetching an index file and extracting relevant markdown pages. covers common mlflow topics, apis, and integrations but procedure is incomplete and failure modes are unaddressed.

Instruments Python and TypeScript code with MLflow Tracing for observability. Must be loaded when setting up tracing as part of any workflow including agent…

Retrieves MLflow traces using CLI or Python API. Use when the user asks to get a trace by ID, find traces, filter traces by status/tags/metadata/execution…

Fetches aggregated trace metrics (token usage, latency, trace counts, quality evaluations) from MLflow tracking servers. Triggers on requests to show metrics,…

Analyzes an MLflow session — a sequence of traces from a multi-turn chat conversation or interaction. Use when the user asks to debug a chat conversation,…

Use this when you need to EVALUATE OR IMPROVE or OPTIMIZE an existing LLM agent's output quality - including improving tool selection accuracy, answer quality,…