What You Can Ask
Ask Struct works across your entire connected stack. Some examples of what you can explore:Alert Analysis
Break down common alerts, identify patterns, and surface recurring issues from your alerting sources.
System Health
Summarize current system health using connected monitors, metrics, and recent error trends.
Issue Investigation
Investigate a specific error, incident, or alert — Struct cross-references logs, traces, and code to find root cause.
Code Context
Ask about recent commits, code paths, and how changes may relate to production issues.
How It Works
- Type your question in the Ask Struct input box
- Struct creates an investigation session and begins gathering context from your connected sources
- You’ll see a structured report with findings, root cause analysis, and suggested next steps
- Continue the conversation — ask follow-up questions to dive deeper
Tips
- Be specific — “Investigate the 500 errors in the checkout API” works better than “What’s wrong?”
- Reference services — Mention specific service names, endpoints, or error messages for more targeted results
- Connect more sources — The more observability tools you connect, the more comprehensive the analysis. See Connections.
Each investigation uses credits from your plan. See Usage & Credits for details.