Honeycomb plugin for Claude

Migrating from Honeycomb Beelines (End of Life) to OpenTelemetry. Trigger phrases: "migrate from Beelines", "upgrade from Beeline to OpenTelemetry", "migrate to OTel", "replace Beelines", "Beeline end of life", "Beeli…

Design and create a Honeycomb board (dashboard) with queries and SLOs. Trigger phrases: "make a board", "build a dashboard", "create a Honeycomb board", "make a dashboard in Honeycomb", "set up a board", "dashboard fo…

Querying OpenTelemetry metrics datasets in Honeycomb, whose rules differ from trace/event datasets: bare COUNT, RATE_SUM, RATE_AVG, RATE_MAX and CONCURRENCY are forbidden, temporal aggregation is automatic, and each m…

First principles of observability: wide events, high cardinality, the core analysis loop, events vs metrics vs logs, and how instrumentation connects to debugging. Trigger phrases: "what is observability", "why observ…

Instrumenting GenAI/LLM applications with OpenTelemetry for Honeycomb, including content capture and agent failure detection. Trigger phrases: "instrument my GenAI app", "add tracing to LLM calls", "trace AI agent", "…

OpenTelemetry SDK setup, custom instrumentation, and sending data to Honeycomb. Trigger phrases: "instrument my app", "add tracing", "set up OpenTelemetry", "configure OTel", "add custom spans", "add attributes to spa…

Retrofitting OpenTelemetry into an existing, uninstrumented application. Trigger phrases: "migrate existing app to OTel", "add OpenTelemetry to existing project", "retrofit OTel into my codebase", "thread context thro…

Workflows for investigating production issues in Honeycomb: context priming, broad query, BubbleUp, trace analysis, verification, and chaining results between steps to a root cause. Trigger phrases: "investigate produ…

Constructing and interpreting Honeycomb queries on trace, log and event datasets: operation selection (percentiles not AVG, HEATMAP for distributions), relational fields (root., parent., any., none.), calculated field…

Interpreting Honeycomb SLO compliance, burn rates and trigger status, and what to do about them: detecting misconfigured SLIs, freezing deploys vs paging on-call, designing burn alert thresholds. Load before calling g…

Find a recent trace in Honeycomb, to see what happened in a recent test. Use when asked to "verify in Honeycomb", "find the most recent trace", or "show me the trace".