Skip to content

add documentation for llm obs insights #30487

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 1 commit into from
Closed
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 5 additions & 0 deletions config/_default/menus/main.en.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -4679,6 +4679,11 @@ menu:
parent: llm_obs_evaluations
identifier: llm_obs_submit_evaluations
weight: 804
- name: LLM Observability Insights
url: llm_observability/monitoring/llm_observability_insights
parent: llm_obs_evaluations
identifier: llm_obs_llm_observability_insights
weight: 805
- name: Experiments
url: llm_observability/experiments_preview
parent: llm_obs
Expand Down
Original file line number Diff line number Diff line change
@@ -0,0 +1,16 @@
---
title: LLM Observabilty Insights
aliases:
- /llm_observability/llm_observability_insights

## Overview

LLM Observability Insights provides a powerful monitoring experience that helps users quickly identify anomalies in their operational metrics—such as latency (duration), error rates, and out-of-the-box (OOTB) evaluation results.

Check warning on line 8 in content/en/llm_observability/monitoring/llm_observability_insights.md

View workflow job for this annotation

GitHub Actions / vale

Datadog.words

Use '' instead of 'quickly'.

Check notice on line 8 in content/en/llm_observability/monitoring/llm_observability_insights.md

View workflow job for this annotation

GitHub Actions / vale

Datadog.sentencelength

Suggestion: Try to keep your sentence length to 25 words or fewer.

Check warning on line 8 in content/en/llm_observability/monitoring/llm_observability_insights.md

View workflow job for this annotation

GitHub Actions / vale

Datadog.words

Use '' instead of 'quickly'.

Check notice on line 8 in content/en/llm_observability/monitoring/llm_observability_insights.md

View workflow job for this annotation

GitHub Actions / vale

Datadog.sentencelength

Suggestion: Try to keep your sentence length to 25 words or fewer.

Outlier detection is performed across key dimensions, including:
- Span name
- Workflow type
- Cluster input/output topics

These outliers are analyzed over the past week and automatically surfaced in the corresponding time window selected by the user. This enables teams to proactively detect regressions, performance drifts, or unexpected behavior in their LLM pipelines.

Loading