See every token.
Debug any trace.
OpenTelemetry-native tracing for LLM apps. Instrument once and inspect every LLM call, tool call, and RAG retrieval across dev, staging, and production - with cost and latency on every span.
The new trace explorer.
Ask for the traces you need, visualize them however debugging demands, and save the views you return to, all on top of the observability you already rely on.
Gantt-style timeline. Every span is a row; the bar shows when it started and how long it ran. The fastest way to spot slow steps.
Ask the explorer in plain English, "show me the top 10 traces with errors", instead of building filters by hand. A faster way to debug.
Waterfall, flame charts, span lists, topology graphs, and sequence diagrams for agentic systems, so unexpected tool-call patterns stand out.
Inspect input and output in a pretty view, or as plain text, JSON, or markdown. Your preferred way of looking at the data.
See input/output sequencing and the complete agent-to-agent communication trail, visibility that basic logs simply cannot give you.
Filter by model, project, labels, metadata, and origin (application, eval, simulation), then build datasets straight from selected traces.
Save a view as a lens. Come back to traces and your layout, filters, and columns are exactly how you left them.
And all the observability you already count on: errors in one place, cost, tokens, duration, models, events, evals, and annotations, ready to build graphs from straight off your traces.
Already works with your whole stack.
LangWatch traces are standard OpenTelemetry spans, enriched with semantic attributes (langwatch.span.type, langwatch.inputs, langwatch.outputs). Keep them in LangWatch, or fan them out to Grafana, Datadog, Jaeger, or any OTel backend you already run. Same spans, every backend.
