Issue Management
After Latitude discovers an issue, use the issue detail view to decide whether to investigate, monitor, resolve, or ignore it.Triage Workflow
When a new issue appears:- Review the description to understand the discovered failure pattern.
- Open example traces to see the conversations where it occurred.
- Assess severity: safety risk, quality degradation, or minor edge case.
- Choose an action:
- Generate an evaluation for ongoing monitoring.
- Resolve it if the problem is already fixed.
- Ignore it if it is noise or too rare to track.
Investigating an Issue
For issues that need deeper investigation, review several example traces and ask:- What user inputs trigger the issue?
- Is the agent consistently wrong, or is the failure intermittent?
- Are there shared patterns in context, tools, retrieval, model, or prompt behavior?
- If evaluations are linked, are they too strict, too lenient, or drifting from human review?
Resolving Issues
When the underlying problem is fixed:- Open the issue detail page.
- Click Resolve.
- Choose whether to keep monitoring.
- Enabled: Linked evaluations stay active and can move the issue to Regressed if the failure returns.
- Disabled: Linked evaluations are archived when the issue resolves.
Working with Regressed Issues
A regressed issue is a previously resolved problem that has returned. Treat it as high priority:- Review the new occurrence traces and confirm they match the original failure pattern.
- Compare them with the original fix and resolution notes.
- Fix the cause and resolve the issue again.
Ignoring Issues
Ignoring is different from resolving:- Ignoring immediately archives all linked evaluations, regardless of the keep-monitoring setting.
- Ignored issues are hidden from default views but can be restored later.
- Use ignore for noise, not for problems that have been fixed.
Keeping Issues Manageable
As your project matures:- Resolve fixed issues instead of leaving them open.
- Keep monitoring enabled when regressions matter.
- Ignore irrelevant issues so real problems stay visible.
- Keep issue descriptions clear enough for future teammates.
- Link meaningful issues to evaluations when you need ongoing coverage.
Next Steps
- Issues Overview: How issues are discovered
- Evaluations: Generate monitors from issues
- Annotations: Leave human feedback on issue traces