# Monitor for issues in your AI application

Canonical: https://brew.new/templates/langfuse/monitor-for-issues-in-your-ai-application

Brand: langfuse.com
Category: onboarding

![Preview of Monitor for issues in your AI application](https://cdn.brew.new/email-preview-4de49b72c121e5e8-tracking_r57ht8529spndt7gv1wjepc8ms8grd0q-1793031741976.png)

## Email content

Hey Alex Reed,

Reading traces one by one does not scale over time. That's where evaluators come in: they score traces for you, so the bad runs are surfaced automatically. We call this monitoring and it represents the second step of the AI Engineering Loop.

Choose what to evaluate

Don't try to cover every failure mode up front. Pick the one failure or signal you've already seen with your own eyes or do error analysis on your traces to identify a failure mode. You can also review our template gallery to get inspiration.

Set up your first evaluator

Score every trace against one thing you care about. You can use LLM-as-a-judge, custom code evals, or user feedback, and track the trend on a dashboard or use the scores to filter on interesting traces.

Full detail in the evaluation docs and the academy.

Best,

Marc

Co-founder, Langfuse (part of Clickhouse)

Links: Roadmap, Docs, Talk to us, Example Project

You are receiving this email because you opted in to receive email from the list Onboarding Journey from Langfuse

Langfuse, Langfuse GmbH, Oranienburger Strasse 91, 10178, Berlin, Germany

Unsubscribe

[Open and remix this design](https://brew.new/templates/langfuse/monitor-for-issues-in-your-ai-application)

[Browse email designs](https://brew.new/browse/templates)