Pulse: find the outliers in your traces
Nikita KabardinA compact chart strip above the events table. See cost, latency, and token spikes over time, then click or drag a spike to narrow the table to that window.
The events table is where you go when something in your traces looks off. Pulse puts a compact chart strip right above it, so the spikes in your data are the first thing you see. Each bar covers a slice of time and shows the worst single event in that slice: the most expensive call, the slowest response, the biggest token burst. The outlier you are hunting for is a tall bar, not a row you have to sort your way down to.
Find it, then drill into it
Pulse turns spotting an outlier into navigating to it. Click a tall bar and the table narrows to that time window, showing exactly the events that made the spike. Drag across a range of bars to select a wider span; it applies when you let go. Browser Back returns you to where you started, so poking around costs you nothing.
One dropdown switches what the strip plots. You can view Cost, Latency, or Tokens on their own, or all three at once in Split mode. Each metric uses the aggregate that fits it: cost as max or sum, latency as max, p95, or average. The bars are time buckets across your full range, so a quiet stretch reads as a flat baseline rather than empty space.
This is how you hunt down expensive or slow outliers on the Langfuse v4 data model: one cheap aggregate query over time, rather than a per-row sort across your whole dataset.