Skip to main content
When you open Alyx from a trace slideover (click a trace to view its details), Alyx has full context of that trace and exposes skills for deep-dive troubleshooting and analysis.

How to open Alyx

Click a trace to open its details in the slideover, then open the Alyx chat. Alyx has full context of the trace you’re viewing so you can ask questions, run evals, or create datasets without switching context.
Open a trace, then open Alyx from the trace slideover to troubleshoot and analyze

Skills in this surface

  • Trace troubleshooting — Diagnose latency bottlenecks, errors, and unexpected behavior
  • Span analysis — Inspect inputs, outputs, tool calls, and error tracebacks for any span
  • Annotations — Create annotation configs and annotate spans to categorize issues
  • Build evals — Create custom evals based on what you observe in the trace
  • Dataset creation — Add spans to datasets or create synthetic datasets from trace analysis
  • Prompt Hub — Load prompts into the playground, save to hub, save new versions
  • Search — Build filters or find spans via natural language when you need filter syntax
  • Documentation — Get platform docs and support answers

Key skills

SkillDescription
Trace previewGet an overview of the trace structure and span hierarchy
Span dataInspect detailed input/output, latency, and attributes for any span
Find in traceSearch for specific content across the trace
AnnotationsCreate configs and annotate single or multiple spans with labels
Build evalWrite a custom LLM-as-a-judge eval for your use case
Create dataset from spansCreate a dataset from selected trace spans
Append spans to datasetAdd spans from this trace to an existing dataset
Synthetic datasetsCreate or append synthetic data for testing
Prompt HubList, load, and save prompts; save new versions
Choose evalsSelect or attach evals; list dataset evals and online tasks
SearchBuild filters or find spans via natural language
Display query paramsShow the current filter and time range
…and more. Alyx has additional skills for experiments, evaluator updates, and multi-step planning.

Why use Alyx here

When you’re deep in a trace—tracking down a failure, explaining latency, or deciding what to add to a dataset—Alyx is right there with that trace in context. Ask in plain language to understand what happened, annotate issues, build evals from what you see, or pull spans into a dataset. You get answers and next steps without leaving the slideover or re-explaining the trace.

Example prompts

  • “What’s causing the latency in this trace?”
  • “Annotate this span as a hallucination”
  • “Build an eval to check if the response answers the question”
  • “Find all spans that call the search tool”
  • “Create a dataset from the spans with errors”