diff --git a/hugo/config/_default/menus/main.en.yaml b/hugo/config/_default/menus/main.en.yaml
index 9e01add5783..0a0d61d1dcd 100644
--- a/hugo/config/_default/menus/main.en.yaml
+++ b/hugo/config/_default/menus/main.en.yaml
@@ -5669,16 +5669,56 @@ menu:
parent: llm_obs_monitoring
identifier: llm_obs_patterns
weight: 404
+ - name: Evaluations
+ url: llm_observability/investigate/evaluations/
+ parent: llm_obs_monitoring
+ identifier: llm_obs_evaluations
+ weight: 405
+ - name: Custom LLM-as-a-Judge
+ url: llm_observability/investigate/evaluations/llm_as_a_judge_evaluations
+ parent: llm_obs_evaluations
+ identifier: llm_obs_custom_llm_as_a_judge_evaluations
+ weight: 40501
+ - name: Language Mismatch
+ url: llm_observability/investigate/evaluations/language_mismatch
+ parent: llm_obs_evaluations
+ identifier: llm_obs_language_mismatch
+ weight: 40502
+ - name: Sensitive Data Scanner
+ url: llm_observability/investigate/evaluations/managed_evaluations/security_and_safety_evaluations
+ parent: llm_obs_evaluations
+ identifier: llm_obs_sensitive_data_scanner
+ weight: 40503
+ - name: End-User Feedback
+ url: llm_observability/investigate/evaluations/end_user_feedback
+ parent: llm_obs_evaluations
+ identifier: llm_obs_end_user_feedback
+ weight: 40504
+ - name: External Evaluations
+ url: llm_observability/investigate/evaluations/external_evaluations
+ parent: llm_obs_evaluations
+ identifier: llm_obs_external_evaluations
+ weight: 40505
+ - name: Evaluation Developer Guide
+ url: llm_observability/investigate/evaluations/evaluation_developer_guide
+ parent: llm_obs_evaluations
+ identifier: llm_obs_evaluation_developer_guide
+ weight: 40506
+ - name: Compatibility
+ url: llm_observability/investigate/evaluations/compatibility
+ parent: llm_obs_evaluations
+ identifier: llm_obs_evaluation_compatibility
+ weight: 40507
- name: Annotation Queues
url: llm_observability/investigate/annotation_queues
parent: llm_obs_monitoring
identifier: llm_obs_annotation_queues
- weight: 405
+ weight: 406
- name: Export API
url: llm_observability/investigate/export_api
parent: llm_obs_monitoring
identifier: llm_obs_evaluations_export_api
- weight: 406
+ weight: 407
- name: Improve
url: llm_observability/improve/
parent: llm_obs
@@ -5729,51 +5769,16 @@ menu:
parent: llm_obs
identifier: llm_obs_configure
weight: 6
- - name: Evaluations
- url: llm_observability/configure/evaluations/
- parent: llm_obs_configure
- identifier: llm_obs_evaluations
- weight: 601
- - name: Custom LLM-as-a-Judge
- url: llm_observability/configure/evaluations/llm_as_a_judge_evaluations
- parent: llm_obs_evaluations
- identifier: llm_obs_custom_llm_as_a_judge_evaluations
- weight: 60101
- - name: Language Mismatch
- url: llm_observability/configure/evaluations/language_mismatch
- parent: llm_obs_evaluations
- identifier: llm_obs_language_mismatch
- weight: 60102
- - name: Sensitive Data Scanner
- url: llm_observability/configure/evaluations/managed_evaluations/security_and_safety_evaluations
- parent: llm_obs_evaluations
- identifier: llm_obs_sensitive_data_scanner
- weight: 60103
- - name: End-User Feedback
- url: llm_observability/configure/evaluations/end_user_feedback
- parent: llm_obs_evaluations
- identifier: llm_obs_end_user_feedback
- weight: 60104
- - name: Compatibility
- url: llm_observability/configure/evaluations/compatibility
- parent: llm_obs_evaluations
- identifier: llm_obs_evaluation_compatibility
- weight: 60106
- - name: External Evaluations
- url: llm_observability/configure/evaluations/external_evaluations
- parent: llm_obs_evaluations
- identifier: llm_obs_external_evaluations
- weight: 60107
- name: Prompt Management
url: llm_observability/configure/prompt_management
parent: llm_obs_configure
identifier: llm_obs_prompt_management
- weight: 602
+ weight: 601
- name: Automation Rules
url: llm_observability/configure/automation_rules
parent: llm_obs_configure
identifier: llm_obs_monitoring_automation_rules
- weight: 603
+ weight: 602
- name: Data Privacy, Security, and RBAC
url: llm_observability/data_privacy_security_and_rbac
parent: llm_obs
diff --git a/hugo/content/en/llm_observability/_index.md b/hugo/content/en/llm_observability/_index.md
index 22d37a09909..6191897765b 100644
--- a/hugo/content/en/llm_observability/_index.md
+++ b/hugo/content/en/llm_observability/_index.md
@@ -139,5 +139,5 @@ See the [Setup documentation][5] for instructions on instrumenting your LLM appl
[6]: /llm_observability/quickstart
[7]: https://app.datadoghq.com/dash/integration/llm_operational_insights
[8]: /llm_observability/setup/auto_instrumentation
-[9]: /llm_observability/configure/evaluations/managed_evaluations
+[9]: /llm_observability/investigate/evaluations/managed_evaluations
[10]: /llm_observability/investigate/patterns
diff --git a/hugo/content/en/llm_observability/build_with_ai/claude_code_skills.md b/hugo/content/en/llm_observability/build_with_ai/claude_code_skills.md
index 6e36547dd05..5ea51a0734e 100644
--- a/hugo/content/en/llm_observability/build_with_ai/claude_code_skills.md
+++ b/hugo/content/en/llm_observability/build_with_ai/claude_code_skills.md
@@ -4,13 +4,13 @@ aliases:
- /llm_observability/guide/claude_code_skills/
description: Use Datadog's Claude Code skills to classify sessions, diagnose failures, compare experiments, generate Python experiment code, and bootstrap evaluators against your live production data.
further_reading:
- - link: '/llm_observability/configure/evaluations/'
+ - link: '/llm_observability/investigate/evaluations/'
tag: 'Documentation'
text: 'Agent Observability Evaluations'
- link: '/llm_observability/improve/experiments/'
tag: 'Documentation'
text: 'LLM Experiments'
- - link: '/llm_observability/guide/evaluation_developer_guide'
+ - link: '/llm_observability/investigate/evaluations/evaluation_developer_guide'
tag: 'Guide'
text: 'Evaluation Developer Guide: Build custom evaluators'
- link: "https://www.datadoghq.com/blog/bits-evals/"
@@ -302,7 +302,7 @@ If you are new to evaluating an LLM application, the recommended flow is:
[1]: https://claude.ai/code
[2]: /llm_observability/setup/
[3]: /llm_observability/improve/experiments/
-[4]: /llm_observability/guide/evaluation_developer_guide
+[4]: /llm_observability/investigate/evaluations/evaluation_developer_guide
[5]: https://datadoghq.atlassian.net/wiki/spaces/BITSAI/pages/5226692942/pup+CLI
[6]: https://github.com/datadog-labs/agent-skills
[7]: https://github.com/DataDog/llm-observability/tree/main/experiments/notebooks
diff --git a/hugo/content/en/llm_observability/configure/_index.md b/hugo/content/en/llm_observability/configure/_index.md
index acb0cc17d04..834b98bbd78 100644
--- a/hugo/content/en/llm_observability/configure/_index.md
+++ b/hugo/content/en/llm_observability/configure/_index.md
@@ -1,12 +1,11 @@
---
title: Configure Agent Observability
-description: Configure evaluations, prompt management, and automation rules for Agent Observability.
+description: Configure prompt management and automation rules for Agent Observability.
---
-Configure the Agent Observability capabilities that Datadog runs for you, including evaluations, automation rules, and prompt management. Datadog hosts and scales them, so you do not operate your own evaluation, routing, or prompt-serving infrastructure.
+Configure the Agent Observability capabilities that Datadog runs for you, including automation rules and prompt management. Datadog hosts and scales them, so you do not operate your own routing or prompt-serving infrastructure.
{{< whatsnext desc="Configuration options:" >}}
- {{< nextlink href="/llm_observability/configure/evaluations/" >}}Evaluations{{< /nextlink >}}
{{< nextlink href="/llm_observability/configure/prompt_management" >}}Prompt Management{{< /nextlink >}}
{{< nextlink href="/llm_observability/configure/automation_rules" >}}Automation Rules{{< /nextlink >}}
{{< /whatsnext >}}
diff --git a/hugo/content/en/llm_observability/guide/_index.md b/hugo/content/en/llm_observability/guide/_index.md
index 5396a5d9c56..0987cb5b77b 100644
--- a/hugo/content/en/llm_observability/guide/_index.md
+++ b/hugo/content/en/llm_observability/guide/_index.md
@@ -12,12 +12,11 @@ cascade:
{{< nextlink href="/llm_observability/quickstart/" >}}Trace an LLM Application{{< /nextlink >}}
{{< nextlink href="/llm_observability/guide/trace-an-llm-application-in-aws-lambda" >}}Trace an LLM Application in AWS Lambda{{< /nextlink >}}
{{< nextlink href="/llm_observability/guide/monitor_proxy_services" >}}Trace Proxy and Gateway Services{{< /nextlink >}}
- {{< nextlink href="/llm_observability/configure/evaluations/" >}}Evaluations{{< /nextlink >}}
{{< nextlink href="/llm_observability/instrument/agent_observability_and_apm" >}}Using Agent Observability and APM{{< /nextlink >}}
{{< nextlink href="/llm_observability/guide/monitor_mcp_client" >}}Monitor MCP Clients{{< /nextlink >}}
{{< nextlink href="/llm_observability/guide/crewai_guide" >}}Using the Datadog-CrewAI integration for Agent Observability{{< /nextlink >}}
{{< nextlink href="/llm_observability/guide/nextjs_guide" >}}Instrument a Next.js Application for Agent Observability{{< /nextlink >}}
{{< nextlink href="/llm_observability/guide/agent_monitoring" >}}Agent Monitoring{{< /nextlink >}}
- {{< nextlink href="/llm_observability/configure/evaluations/evaluation_developer_guide" >}}Evaluation Developer Guide: Build custom evaluators{{< /nextlink >}}
+ {{< nextlink href="/llm_observability/investigate/evaluations/evaluation_developer_guide" >}}Evaluation Developer Guide: Build custom evaluators{{< /nextlink >}}
{{< nextlink href="/llm_observability/build_with_ai/claude_code_skills" >}}Analyze LLM Applications with Claude Code Skills{{< /nextlink >}}
{{< /whatsnext >}}
diff --git a/hugo/content/en/llm_observability/improve/experiments/setup.md b/hugo/content/en/llm_observability/improve/experiments/setup.md
index ef1a85e833b..b59a77754ec 100644
--- a/hugo/content/en/llm_observability/improve/experiments/setup.md
+++ b/hugo/content/en/llm_observability/improve/experiments/setup.md
@@ -347,7 +347,7 @@ Note: LLM Experiments traces are retained for 90 days.
[1]: /llm_observability/improve/datasets
[2]: /llm_observability/instrument/custom_instrumentation?tab=decorators#trace-an-llm-application
[3]: /llm_observability/instrument/auto_instrumentation?tab=python
-[4]: /llm_observability/guide/evaluation_developer_guide
+[4]: /llm_observability/investigate/evaluations/evaluation_developer_guide
[5]: /llm_observability/instrument/agent_observability_and_apm/
[6]: /llm_observability/instrument/otel_instrumentation
diff --git a/hugo/content/en/llm_observability/instrument/api.md b/hugo/content/en/llm_observability/instrument/api.md
index 7cb8340647b..d8275086e97 100644
--- a/hugo/content/en/llm_observability/instrument/api.md
+++ b/hugo/content/en/llm_observability/instrument/api.md
@@ -374,7 +374,7 @@ The name can be up to 193 characters long and may not contain contiguous or trai
## Evaluations API
-
+
Use this endpoint to send evaluations and end-user feedback to Datadog. Evaluations can be associated with spans, traces, or sessions. End-user feedback can be associated with spans, traces, sessions, or a customer-defined feedback join key.
@@ -702,5 +702,5 @@ For feedback events, provide exactly one of `span_id`, `trace_id`, `session_id`,
[1]: /llm_observability/setup/sdk/
[2]: /llm_observability/quickstart/terms/
[3]: /getting_started/tagging/
-[4]: /llm_observability/configure/evaluations/end_user_feedback
+[4]: /llm_observability/investigate/evaluations/end_user_feedback
[5]: /llm_observability/instrument/sdk/?tab=python#enriching-spans
diff --git a/hugo/content/en/llm_observability/instrument/otel_instrumentation.md b/hugo/content/en/llm_observability/instrument/otel_instrumentation.md
index a8d92303249..68f3a4a123d 100644
--- a/hugo/content/en/llm_observability/instrument/otel_instrumentation.md
+++ b/hugo/content/en/llm_observability/instrument/otel_instrumentation.md
@@ -19,7 +19,7 @@ Agent Observability supports ingesting OpenTelemetry traces that follow either t
### Evaluations
-To send [external evaluations directly to the API](/llm_observability/configure/evaluations/external_evaluations#submitting-external-evaluations-with-the-api) for OpenTelemetry spans, include the `source:otel` tag in the evaluation. When referencing spans, provide `span_id` and `trace_id` as decimal strings. OpenTelemetry uses hexadecimal IDs natively, so convert them to decimal before submitting evaluations. For example, use Python's `int(hex_span_id, 16)` to convert a hex span ID to its decimal equivalent.
+To send [external evaluations directly to the API](/llm_observability/investigate/evaluations/external_evaluations#submitting-external-evaluations-with-the-api) for OpenTelemetry spans, include the `source:otel` tag in the evaluation. When referencing spans, provide `span_id` and `trace_id` as decimal strings. OpenTelemetry uses hexadecimal IDs natively, so convert them to decimal before submitting evaluations. For example, use Python's `int(hex_span_id, 16)` to convert a hex span ID to its decimal equivalent.
### Prompt Tracking
@@ -944,7 +944,7 @@ with tracer.start_as_current_span("my-span") as span:
[3]: https://app.datadoghq.com/llm/traces
[4]: /help/
[5]: https://pypi.org/project/strands-agents/
-[6]: /llm_observability/configure/evaluations/external_evaluations
+[6]: /llm_observability/investigate/evaluations/external_evaluations
[7]: https://strandsagents.com/latest/
[8]: /account_management/rbac/data_access/
[9]: https://opentelemetry.io/docs/concepts/signals/traces/#span-links
diff --git a/hugo/content/en/llm_observability/instrument/sdk.md b/hugo/content/en/llm_observability/instrument/sdk.md
index 12a8fdfcd66..50261dea7ee 100644
--- a/hugo/content/en/llm_observability/instrument/sdk.md
+++ b/hugo/content/en/llm_observability/instrument/sdk.md
@@ -1959,8 +1959,8 @@ Supported keys:
- `template` (str): Template string with placeholders (for example, `"Translate {{text}} to {{lang}}"`).
- `chat_template` (List[Message]): Multi-message template form. Provide a list of `{ "role": "", "content": "" }` objects.
- `tags` (Dict[str, str]): Tags to attach to the prompt run.
-- `rag_context_variables` (List[str]): Variable keys that contain ground-truth/context content. Used for [hallucination detection](/llm_observability/configure/evaluations/llm_as_a_judge_evaluations/template_evaluations#hallucination).
-- `rag_query_variables` (List[str]): Variable keys that contain the user query. Used for [hallucination detection](/llm_observability/configure/evaluations/llm_as_a_judge_evaluations/template_evaluations#hallucination).
+- `rag_context_variables` (List[str]): Variable keys that contain ground-truth/context content. Used for [hallucination detection](/llm_observability/investigate/evaluations/llm_as_a_judge_evaluations/template_evaluations#hallucination).
+- `rag_query_variables` (List[str]): Variable keys that contain the user query. Used for [hallucination detection](/llm_observability/investigate/evaluations/llm_as_a_judge_evaluations/template_evaluations#hallucination).
{{% /collapse-content %}}
@@ -2021,8 +2021,8 @@ Supported properties:
- `variables` (Record): Variables used to populate the template placeholders.
- `template` (string | List[Message]): Template string with placeholders (for example, `"Translate {{text}} to {{lang}}"`). Alternatively, a list of `{ "role": "", "content": "" }` objects.
- `tags` (Record): Tags to attach to the prompt run.
-- `contextVariables` (string[]): Variable keys that contain ground-truth/context content. Used for [hallucination detection](/llm_observability/configure/evaluations/llm_as_a_judge_evaluations/template_evaluations#hallucination).
-- `queryVariables` (string[]): Variable keys that contain the user query. Used for [hallucination detection](/llm_observability/configure/evaluations/llm_as_a_judge_evaluations/template_evaluations#hallucination).
+- `contextVariables` (string[]): Variable keys that contain ground-truth/context content. Used for [hallucination detection](/llm_observability/investigate/evaluations/llm_as_a_judge_evaluations/template_evaluations#hallucination).
+- `queryVariables` (string[]): Variable keys that contain the user query. Used for [hallucination detection](/llm_observability/investigate/evaluations/llm_as_a_judge_evaluations/template_evaluations#hallucination).
{{% /collapse-content %}}
@@ -2338,7 +2338,7 @@ llmobs.annotationContext({
The Agent Observability SDK provides methods to export and submit your evaluations to Datadog.
-For building reusable, class-based evaluators (
BaseEvaluator,
BaseSummaryEvaluator) with rich result metadata, see the
Evaluation Developer Guide.
+For building reusable, class-based evaluators (
BaseEvaluator,
BaseSummaryEvaluator) with rich result metadata, see the
Evaluation Developer Guide.
Evaluations must be joined to a single span. You can identify the target span using either of these two methods:
- _Tag-based joining_ - Join an evaluation using a unique key-value tag pair that is set on a single span. The evaluation will fail to join if the tag key-value pair matches multiple spans or no spans.
diff --git a/hugo/content/en/llm_observability/investigate/_index.md b/hugo/content/en/llm_observability/investigate/_index.md
index 6eede28ad24..97a052ee938 100644
--- a/hugo/content/en/llm_observability/investigate/_index.md
+++ b/hugo/content/en/llm_observability/investigate/_index.md
@@ -87,6 +87,6 @@ Learn how to monitor agentic LLM applications, which use multiple tools or chain
[2]: /llm_observability/instrument/agent_observability_and_apm
[3]: /llm_observability/investigate/patterns/
[4]: /llm_observability/guide/agent_monitoring
-[5]: /llm_observability/configure/evaluations/
+[5]: /llm_observability/investigate/evaluations/
[6]: https://app.datadoghq.com/dash/integration/llm_operational_insights?fromUser=false&refresh_mode=sliding&from_ts=1758905575629&to_ts=1758909175629&live=true
[7]: /llm_observability/configure/prompt_management
diff --git a/hugo/content/en/llm_observability/investigate/annotation_queues.md b/hugo/content/en/llm_observability/investigate/annotation_queues.md
index 09e3ba0a7dd..80cc2cfce8a 100644
--- a/hugo/content/en/llm_observability/investigate/annotation_queues.md
+++ b/hugo/content/en/llm_observability/investigate/annotation_queues.md
@@ -4,7 +4,7 @@ aliases:
- /llm_observability/evaluations/annotation_queues/
description: Enable systematic human review of LLM traces to identify failure modes, validate automated evaluations, and build golden datasets.
further_reading:
- - link: /llm_observability/configure/evaluations/
+ - link: /llm_observability/investigate/evaluations/
tag: Documentation
text: Learn about evaluation types
- link: /llm_observability/configure/automation_rules
diff --git a/hugo/content/en/llm_observability/configure/evaluations/_index.md b/hugo/content/en/llm_observability/investigate/evaluations/_index.md
similarity index 88%
rename from hugo/content/en/llm_observability/configure/evaluations/_index.md
rename to hugo/content/en/llm_observability/investigate/evaluations/_index.md
index c5aad7a63d2..2e543475855 100644
--- a/hugo/content/en/llm_observability/configure/evaluations/_index.md
+++ b/hugo/content/en/llm_observability/investigate/evaluations/_index.md
@@ -5,6 +5,7 @@ aliases:
- /tracing/llm_observability/evaluations/
- /llm_observability/configuration/
- /llm_observability/evaluations/
+ - /llm_observability/configure/evaluations/
further_reading:
- link: https://www.datadoghq.com/blog/llm-prompt-tracking
@@ -67,15 +68,15 @@ Agent Observability offers an [Export API][9] that you can use to retrieve spans
{{< partial name="whats-next/whats-next.html" >}}
-[1]: /llm_observability/configure/evaluations/llm_as_a_judge_evaluations
-[2]: /llm_observability/configure/evaluations/managed_evaluations
-[3]: /llm_observability/configure/evaluations/external_evaluations
-[5]: /llm_observability/configure/evaluations/external_evaluations/nemo
+[1]: /llm_observability/investigate/evaluations/llm_as_a_judge_evaluations
+[2]: /llm_observability/investigate/evaluations/managed_evaluations
+[3]: /llm_observability/investigate/evaluations/external_evaluations
+[5]: /llm_observability/investigate/evaluations/external_evaluations/nemo
[6]: /security/sensitive_data_scanner/
[7]: /account_management/rbac/permissions/#llm-observability
[8]: https://app.datadoghq.com/llm/evaluations
[9]: /llm_observability/investigate/export_api
-[10]: /llm_observability/guide/evaluation_developer_guide
+[10]: /llm_observability/investigate/evaluations/evaluation_developer_guide
[11]: /llm_observability/investigate/annotation_queues
[12]: /security/sensitive_data_scanner/scanning_rules/library_rules/
-[13]: /llm_observability/configure/evaluations/end_user_feedback
+[13]: /llm_observability/investigate/evaluations/end_user_feedback
diff --git a/hugo/content/en/llm_observability/configure/evaluations/compatibility.md b/hugo/content/en/llm_observability/investigate/evaluations/compatibility.md
similarity index 67%
rename from hugo/content/en/llm_observability/configure/evaluations/compatibility.md
rename to hugo/content/en/llm_observability/investigate/evaluations/compatibility.md
index 1dd6b6bc071..6bc832ee8d3 100644
--- a/hugo/content/en/llm_observability/configure/evaluations/compatibility.md
+++ b/hugo/content/en/llm_observability/investigate/evaluations/compatibility.md
@@ -2,6 +2,7 @@
title: Evaluation compatibility
aliases:
- /llm_observability/evaluations/evaluation_compatibility/
+- /llm_observability/configure/evaluations/compatibility/
description: Learn about the compatibility requirements for evaluations.
---
@@ -45,14 +46,14 @@ Existing templates for custom LLM-as-a-judge evaluations are supported for the f
| [Goal Completeness][3] | Fully supported | All third party LLM providers | LLM only |
-[1]: /llm_observability/configure/evaluations/llm_as_a_judge_evaluations/template_evaluations#tool-selection
-[2]: /llm_observability/configure/evaluations/llm_as_a_judge_evaluations/template_evaluations#tool-argument-correctness
-[3]: /llm_observability/configure/evaluations/llm_as_a_judge_evaluations/template_evaluations#goal-completeness
-[4]: /llm_observability/configure/evaluations/llm_as_a_judge_evaluations/template_evaluations#hallucination
-[5]: /llm_observability/configure/evaluations/llm_as_a_judge_evaluations/template_evaluations#failure-to-answer
-[6]: /llm_observability/configure/evaluations/llm_as_a_judge_evaluations/template_evaluations#sentiment
-[7]: /llm_observability/configure/evaluations/llm_as_a_judge_evaluations/template_evaluations#toxicity
-[8]: /llm_observability/configure/evaluations/llm_as_a_judge_evaluations/template_evaluations#prompt-injection
-[9]: /llm_observability/configure/evaluations/llm_as_a_judge_evaluations/template_evaluations#topic-relevancy
-[10]: /llm_observability/configure/evaluations/managed_evaluations#language-mismatch
-[11]: /llm_observability/configure/evaluations/llm_as_a_judge_evaluations#define-the-evaluation-output
+[1]: /llm_observability/investigate/evaluations/llm_as_a_judge_evaluations/template_evaluations#tool-selection
+[2]: /llm_observability/investigate/evaluations/llm_as_a_judge_evaluations/template_evaluations#tool-argument-correctness
+[3]: /llm_observability/investigate/evaluations/llm_as_a_judge_evaluations/template_evaluations#goal-completeness
+[4]: /llm_observability/investigate/evaluations/llm_as_a_judge_evaluations/template_evaluations#hallucination
+[5]: /llm_observability/investigate/evaluations/llm_as_a_judge_evaluations/template_evaluations#failure-to-answer
+[6]: /llm_observability/investigate/evaluations/llm_as_a_judge_evaluations/template_evaluations#sentiment
+[7]: /llm_observability/investigate/evaluations/llm_as_a_judge_evaluations/template_evaluations#toxicity
+[8]: /llm_observability/investigate/evaluations/llm_as_a_judge_evaluations/template_evaluations#prompt-injection
+[9]: /llm_observability/investigate/evaluations/llm_as_a_judge_evaluations/template_evaluations#topic-relevancy
+[10]: /llm_observability/investigate/evaluations/language_mismatch
+[11]: /llm_observability/investigate/evaluations/llm_as_a_judge_evaluations#define-the-evaluation-output
diff --git a/hugo/content/en/llm_observability/configure/evaluations/end_user_feedback.md b/hugo/content/en/llm_observability/investigate/evaluations/end_user_feedback.md
similarity index 95%
rename from hugo/content/en/llm_observability/configure/evaluations/end_user_feedback.md
rename to hugo/content/en/llm_observability/investigate/evaluations/end_user_feedback.md
index e8850eb3784..0473f948982 100644
--- a/hugo/content/en/llm_observability/configure/evaluations/end_user_feedback.md
+++ b/hugo/content/en/llm_observability/investigate/evaluations/end_user_feedback.md
@@ -2,12 +2,13 @@
title: End-User Feedback
aliases:
- /llm_observability/evaluations/end_user_feedback/
+- /llm_observability/configure/evaluations/end_user_feedback/
description: Submit end-user feedback to Agent Observability and connect it to spans, traces, sessions, or external entities.
further_reading:
- link: '/llm_observability/instrument/api/#evaluations-api'
tag: 'Documentation'
text: 'Learn about the Evaluations API'
- - link: '/llm_observability/configure/evaluations/external_evaluations'
+ - link: '/llm_observability/investigate/evaluations/external_evaluations'
tag: 'Documentation'
text: 'Learn about submitting external evaluations'
- link: '/llm_observability/investigate/annotation_queues'
@@ -120,7 +121,7 @@ To create a dashboard widget for feedback, create the widget as you would for an
{{< partial name="whats-next/whats-next.html" >}}
-[1]: /llm_observability/configure/evaluations/external_evaluations
+[1]: /llm_observability/investigate/evaluations/external_evaluations
[2]: /llm_observability/investigate/annotation_queues
[3]: /llm_observability/instrument/api/#evaluations-api
[4]: /llm_observability/instrument/sdk/?tab=python#enriching-spans
diff --git a/hugo/content/en/llm_observability/configure/evaluations/evaluation_developer_guide.md b/hugo/content/en/llm_observability/investigate/evaluations/evaluation_developer_guide.md
similarity index 98%
rename from hugo/content/en/llm_observability/configure/evaluations/evaluation_developer_guide.md
rename to hugo/content/en/llm_observability/investigate/evaluations/evaluation_developer_guide.md
index 22b4351cd74..8e23689e752 100644
--- a/hugo/content/en/llm_observability/configure/evaluations/evaluation_developer_guide.md
+++ b/hugo/content/en/llm_observability/investigate/evaluations/evaluation_developer_guide.md
@@ -3,9 +3,10 @@ title: Evaluation Developer Guide
aliases:
- /llm_observability/guide/evaluation_developer_guide
- /llm_observability/evaluations/evaluation_developer_guide/
+ - /llm_observability/configure/evaluations/evaluation_developer_guide/
description: Learn how to build custom evaluators using the Agent Observability SDK.
further_reading:
- - link: '/llm_observability/configure/evaluations/external_evaluations'
+ - link: '/llm_observability/investigate/evaluations/external_evaluations'
tag: 'Documentation'
text: 'Learn about submitting external evaluations'
- link: '/llm_observability/setup/sdk/python'
@@ -646,7 +647,7 @@ except RemoteEvaluatorError as e:
## Using evaluators in production
-This section covers evaluations you run and submit manually from your application code. To have Datadog run evaluations automatically on production traces, see
Custom LLM-as-a-Judge Evaluations instead.
+This section covers evaluations you run and submit manually from your application code. To have Datadog run evaluations automatically on production traces, see
Custom LLM-as-a-Judge Evaluations instead.
To submit evaluations from your application code, construct the `EvaluatorContext` yourself, call the evaluator, and submit the result with `LLMObs.submit_evaluation()`. You can also submit evaluations through the HTTP API.
@@ -776,11 +777,11 @@ When submitting evaluations for [OpenTelemetry-instrumented spans][3], include t
{{< partial name="whats-next/whats-next.html" >}}
-[1]: /llm_observability/configure/evaluations/external_evaluations
+[1]: /llm_observability/investigate/evaluations/external_evaluations
[2]: /llm_observability/instrument/api/#evaluations-api
[3]: /llm_observability/instrument/otel_instrumentation
[4]: /llm_observability/improve/experiments
-[5]: /llm_observability/configure/evaluations/llm_as_a_judge_evaluations
-[6]: /llm_observability/configure/evaluations/external_evaluations/deepeval/
-[7]: /llm_observability/configure/evaluations/llm_as_a_judge_evaluations#configure-the-prompt
-[8]: /llm_observability/configure/evaluations/external_evaluations/pydantic
+[5]: /llm_observability/investigate/evaluations/llm_as_a_judge_evaluations
+[6]: /llm_observability/investigate/evaluations/external_evaluations/deepeval/
+[7]: /llm_observability/investigate/evaluations/llm_as_a_judge_evaluations#configure-the-prompt
+[8]: /llm_observability/investigate/evaluations/external_evaluations/pydantic
diff --git a/hugo/content/en/llm_observability/configure/evaluations/external_evaluations/_index.md b/hugo/content/en/llm_observability/investigate/evaluations/external_evaluations/_index.md
similarity index 84%
rename from hugo/content/en/llm_observability/configure/evaluations/external_evaluations/_index.md
rename to hugo/content/en/llm_observability/investigate/evaluations/external_evaluations/_index.md
index 79c18ada96f..6be04238662 100644
--- a/hugo/content/en/llm_observability/configure/evaluations/external_evaluations/_index.md
+++ b/hugo/content/en/llm_observability/investigate/evaluations/external_evaluations/_index.md
@@ -7,8 +7,9 @@ aliases:
- /llm_observability/evaluations/submit_evaluations
- /llm_observability/configure/evaluations/submit_evaluations
- /llm_observability/evaluations/external_evaluations/
+ - /llm_observability/configure/evaluations/external_evaluations/
further_reading:
- - link: '/llm_observability/guide/evaluation_developer_guide'
+ - link: '/llm_observability/investigate/evaluations/evaluation_developer_guide'
tag: 'Documentation'
text: 'Learn about building custom evaluators'
- link: '/llm_observability/setup/sdk'
@@ -17,10 +18,10 @@ further_reading:
- link: '/llm_observability/setup/api'
tag: 'Documentation'
text: 'Learn about the Evaluations API'
- - link: '/llm_observability/configure/evaluations/external_evaluations/nemo'
+ - link: '/llm_observability/investigate/evaluations/external_evaluations/nemo'
tag: 'Documentation'
text: 'Learn about submitting evaluations from NVIDIA NeMo'
- - link: '/llm_observability/configure/evaluations/end_user_feedback'
+ - link: '/llm_observability/investigate/evaluations/end_user_feedback'
tag: 'Documentation'
text: 'Learn about submitting end-user feedback'
---
@@ -42,13 +43,13 @@ Evaluation labels must be unique for a given LLM application (ml_app
-For feedback submitted by your users such as thumbs-up or thumbs-down ratings, accepted changes, free-text comments, and other signals, see
End-User Feedback.
+For feedback submitted by your users such as thumbs-up or thumbs-down ratings, accepted changes, free-text comments, and other signals, see
End-User Feedback.
## Submitting external evaluations with the SDK
The Agent Observability SDK provides the methods `LLMObs.submit_evaluation()` and `LLMObs.export_span()` to help your traced LLM application submit external evaluations to Agent Observability. See the [Python][3] or [Node.js][4] SDK documentation for more details.
-
+
### Example
@@ -122,9 +123,9 @@ To submit evaluations for }}
- {{< nextlink href="/llm_observability/configure/evaluations/external_evaluations/deepeval" >}}DeepEval Evaluations{{< /nextlink >}}
- {{< nextlink href="/llm_observability/configure/evaluations/external_evaluations/pydantic" >}}Pydantic Evaluations{{< /nextlink >}}
- {{< nextlink href="/llm_observability/configure/evaluations/external_evaluations/nemo" >}}NeMo Evaluations{{< /nextlink >}}
+ {{< nextlink href="/llm_observability/investigate/evaluations/external_evaluations/deepeval" >}}DeepEval Evaluations{{< /nextlink >}}
+ {{< nextlink href="/llm_observability/investigate/evaluations/external_evaluations/pydantic" >}}Pydantic Evaluations{{< /nextlink >}}
+ {{< nextlink href="/llm_observability/investigate/evaluations/external_evaluations/nemo" >}}NeMo Evaluations{{< /nextlink >}}
{{< /whatsnext >}}
## Further Reading
@@ -135,4 +136,4 @@ To submit evaluations for If you already have an LLMJudge defined in the SDK, you can publish it directly to Datadog without rebuilding the configuration in the UI. See Publishing an LLMJudge as a Datadog managed evaluation.
+
Learn more about the [compatibility requirements][6].
@@ -595,21 +596,20 @@ You can use basic CRUD operations to manipulate managed evaluation configs, afte
{{< partial name="whats-next/whats-next.html" >}}
[1]: https://app.datadoghq.com/llm/evaluations
-[2]: /llm_observability/configure/evaluations/llm_as_a_judge_evaluations/connect_to_account
+[2]: /llm_observability/investigate/evaluations/llm_as_a_judge_evaluations/connect_to_account
[3]: /events/explorer/facets/
[4]: /monitors/
[5]: https://arxiv.org/abs/2504.00050
-[6]: /llm_observability/configure/evaluations/compatibility
-[7]: /llm_observability/configure/evaluations/llm_as_a_judge_evaluations/template_evaluations/
+[6]: /llm_observability/investigate/evaluations/compatibility
+[7]: /llm_observability/investigate/evaluations/llm_as_a_judge_evaluations/template_evaluations/
[8]: /llm_observability/improve/experiments
-[9]: /llm_observability/guide/evaluation_developer_guide/#using-managed-evaluators
+[9]: /llm_observability/investigate/evaluations/evaluation_developer_guide/#using-managed-evaluators
[10]: https://app.datadoghq.com/dash/integration/llm_evaluations_token_usage
[11]: /api/latest/agent-observability/#get-a-custom-evaluator-configuration
[12]: /api/latest/agent-observability/#create-or-update-a-custom-evaluator-configuration
[13]: /api/latest/agent-observability/#delete-a-custom-evaluator-configuration
[14]: /account_management/api-app-keys
-[15]: /llm_observability/configure/evaluations/llm_as_a_judge_evaluations/prompt_templating
-[16]: /llm_observability/configure/evaluations/llm_as_a_judge_evaluations/trace_level_evaluations
-[17]: /llm_observability/configure/evaluations/llm_as_a_judge_evaluations/session_level_evaluations
+[15]: /llm_observability/investigate/evaluations/llm_as_a_judge_evaluations/prompt_templating
+[16]: /llm_observability/investigate/evaluations/llm_as_a_judge_evaluations/trace_level_evaluations
+[17]: /llm_observability/investigate/evaluations/llm_as_a_judge_evaluations/session_level_evaluations
[18]: https://docs.cloud.google.com/gemini-enterprise-agent-platform/resources/locations
-
diff --git a/hugo/content/en/llm_observability/configure/evaluations/llm_as_a_judge_evaluations/connect_to_account.md b/hugo/content/en/llm_observability/investigate/evaluations/llm_as_a_judge_evaluations/connect_to_account.md
similarity index 98%
rename from hugo/content/en/llm_observability/configure/evaluations/llm_as_a_judge_evaluations/connect_to_account.md
rename to hugo/content/en/llm_observability/investigate/evaluations/llm_as_a_judge_evaluations/connect_to_account.md
index df98c42bec5..8b7b38f9a40 100644
--- a/hugo/content/en/llm_observability/configure/evaluations/llm_as_a_judge_evaluations/connect_to_account.md
+++ b/hugo/content/en/llm_observability/investigate/evaluations/llm_as_a_judge_evaluations/connect_to_account.md
@@ -2,9 +2,10 @@
title: Connect your LLM provider account
aliases:
- /llm_observability/evaluations/custom_llm_as_a_judge_evaluations/connect_to_account/
+- /llm_observability/configure/evaluations/llm_as_a_judge_evaluations/connect_to_account/
description: How to connect to your LLM provider account to support judge LLM based evaluations
further_reading:
-- link: "/llm_observability/configure/evaluations/llm_as_a_judge_evaluations"
+- link: "/llm_observability/investigate/evaluations/llm_as_a_judge_evaluations"
tag: "Documentation"
text: "Learn about custom LLM-as-a-judge evaluations"
---
@@ -137,4 +138,3 @@ If your LLM provider restricts IP addresses, you can obtain the required IP rang
[1]: https://app.datadoghq.com/llm/settings/integrations
[2]: /api/latest/ip-ranges/
-
diff --git a/hugo/content/en/llm_observability/configure/evaluations/llm_as_a_judge_evaluations/prompt_templating.md b/hugo/content/en/llm_observability/investigate/evaluations/llm_as_a_judge_evaluations/prompt_templating.md
similarity index 93%
rename from hugo/content/en/llm_observability/configure/evaluations/llm_as_a_judge_evaluations/prompt_templating.md
rename to hugo/content/en/llm_observability/investigate/evaluations/llm_as_a_judge_evaluations/prompt_templating.md
index e4c7680195b..1a9d0c405ed 100644
--- a/hugo/content/en/llm_observability/configure/evaluations/llm_as_a_judge_evaluations/prompt_templating.md
+++ b/hugo/content/en/llm_observability/investigate/evaluations/llm_as_a_judge_evaluations/prompt_templating.md
@@ -2,15 +2,16 @@
title: Prompt Templating
aliases:
- /llm_observability/evaluations/custom_llm_as_a_judge_evaluations/prompt_templating/
+- /llm_observability/configure/evaluations/llm_as_a_judge_evaluations/prompt_templating/
description: Reference for the templating used in custom LLM-as-a-judge evaluation prompts—variables, array operators, span and trace filters, session paths, and resolution rules.
further_reading:
-- link: "/llm_observability/configure/evaluations/llm_as_a_judge_evaluations"
+- link: "/llm_observability/investigate/evaluations/llm_as_a_judge_evaluations"
tag: "Documentation"
text: "Custom LLM-as-a-Judge Evaluations"
-- link: "/llm_observability/configure/evaluations/llm_as_a_judge_evaluations/session_level_evaluations"
+- link: "/llm_observability/investigate/evaluations/llm_as_a_judge_evaluations/session_level_evaluations"
tag: "Documentation"
text: "Session-Level Evaluations"
-- link: "/llm_observability/configure/evaluations/llm_as_a_judge_evaluations/trace_level_evaluations"
+- link: "/llm_observability/investigate/evaluations/llm_as_a_judge_evaluations/trace_level_evaluations"
tag: "Documentation"
text: "Trace-Level Evaluations"
---
@@ -182,5 +183,5 @@ For example, given a span where `meta.input.messages` is:
{{< partial name="whats-next/whats-next.html" >}}
[1]: /llm_observability/instrument/sdk/#tracking-user-sessions
-[2]: /llm_observability/configure/evaluations/llm_as_a_judge_evaluations/session_level_evaluations
-[3]: /llm_observability/configure/evaluations/llm_as_a_judge_evaluations/trace_level_evaluations
+[2]: /llm_observability/investigate/evaluations/llm_as_a_judge_evaluations/session_level_evaluations
+[3]: /llm_observability/investigate/evaluations/llm_as_a_judge_evaluations/trace_level_evaluations
diff --git a/hugo/content/en/llm_observability/configure/evaluations/llm_as_a_judge_evaluations/session_level_evaluations.md b/hugo/content/en/llm_observability/investigate/evaluations/llm_as_a_judge_evaluations/session_level_evaluations.md
similarity index 92%
rename from hugo/content/en/llm_observability/configure/evaluations/llm_as_a_judge_evaluations/session_level_evaluations.md
rename to hugo/content/en/llm_observability/investigate/evaluations/llm_as_a_judge_evaluations/session_level_evaluations.md
index 6556f009e3a..a3f8faa89d2 100644
--- a/hugo/content/en/llm_observability/configure/evaluations/llm_as_a_judge_evaluations/session_level_evaluations.md
+++ b/hugo/content/en/llm_observability/investigate/evaluations/llm_as_a_judge_evaluations/session_level_evaluations.md
@@ -2,15 +2,16 @@
title: Session-Level Evaluations
aliases:
- /llm_observability/evaluations/custom_llm_as_a_judge_evaluations/session_level_evaluations/
+- /llm_observability/configure/evaluations/llm_as_a_judge_evaluations/session_level_evaluations/
description: Run a custom LLM-as-a-judge across an entire user session, with examples of when to use session scope over trace or span scope.
further_reading:
-- link: "/llm_observability/configure/evaluations/llm_as_a_judge_evaluations"
+- link: "/llm_observability/investigate/evaluations/llm_as_a_judge_evaluations"
tag: "Documentation"
text: "Custom LLM-as-a-Judge Evaluations"
-- link: "/llm_observability/configure/evaluations/llm_as_a_judge_evaluations/trace_level_evaluations"
+- link: "/llm_observability/investigate/evaluations/llm_as_a_judge_evaluations/trace_level_evaluations"
tag: "Documentation"
text: "Trace-Level Evaluations"
-- link: "/llm_observability/configure/evaluations/llm_as_a_judge_evaluations/prompt_templating"
+- link: "/llm_observability/investigate/evaluations/llm_as_a_judge_evaluations/prompt_templating"
tag: "Documentation"
text: "Prompt Templating"
- link: "/llm_observability/instrument/sdk/#tracking-user-sessions"
@@ -193,13 +194,13 @@ Configuring evaluations requires the `Agent Observability Write` [permission][4]
{{< partial name="whats-next/whats-next.html" >}}
[1]: https://app.datadoghq.com/llm/evaluations
-[2]: /llm_observability/configure/evaluations/llm_as_a_judge_evaluations/template_evaluations
-[3]: /llm_observability/configure/evaluations/llm_as_a_judge_evaluations/prompt_templating
+[2]: /llm_observability/investigate/evaluations/llm_as_a_judge_evaluations/template_evaluations
+[3]: /llm_observability/investigate/evaluations/llm_as_a_judge_evaluations/prompt_templating
[4]: /account_management/rbac/permissions/#llm-observability
-[5]: /llm_observability/configure/evaluations/llm_as_a_judge_evaluations/#define-the-evaluation-output
+[5]: /llm_observability/investigate/evaluations/llm_as_a_judge_evaluations/#define-the-evaluation-output
[6]: /events/explorer/facets/
[7]: /monitors/
[8]: /llm_observability/investigate/annotation_queues
[9]: /llm_observability/instrument/sdk/#tracking-user-sessions
-[10]: /llm_observability/configure/evaluations/llm_as_a_judge_evaluations/trace_level_evaluations
-[11]: /llm_observability/configure/evaluations/llm_as_a_judge_evaluations/template_evaluations/#goal-completeness
+[10]: /llm_observability/investigate/evaluations/llm_as_a_judge_evaluations/trace_level_evaluations
+[11]: /llm_observability/investigate/evaluations/llm_as_a_judge_evaluations/template_evaluations/#goal-completeness
diff --git a/hugo/content/en/llm_observability/configure/evaluations/llm_as_a_judge_evaluations/template_evaluations.md b/hugo/content/en/llm_observability/investigate/evaluations/llm_as_a_judge_evaluations/template_evaluations.md
similarity index 94%
rename from hugo/content/en/llm_observability/configure/evaluations/llm_as_a_judge_evaluations/template_evaluations.md
rename to hugo/content/en/llm_observability/investigate/evaluations/llm_as_a_judge_evaluations/template_evaluations.md
index c2e242729ff..3ab2563c150 100644
--- a/hugo/content/en/llm_observability/configure/evaluations/llm_as_a_judge_evaluations/template_evaluations.md
+++ b/hugo/content/en/llm_observability/investigate/evaluations/llm_as_a_judge_evaluations/template_evaluations.md
@@ -21,6 +21,7 @@ aliases:
- /llm_observability/evaluations/managed_evaluations/session_level_evaluations
- /llm_observability/configure/evaluations/managed_evaluations/session_level_evaluations
- /llm_observability/evaluations/custom_llm_as_a_judge_evaluations/template_evaluations/
+ - /llm_observability/configure/evaluations/llm_as_a_judge_evaluations/template_evaluations/
---
Datadog provides LLM-as-a-judge templates for the following evaluations: [Failure to Answer][16], [Goal Completeness][22], [Hallucination][25], [Prompt Injection][14], [Sentiment][12], [Tool Argument Correctness][23], [Tool Selection][24], [Topic Relevancy][15], and [Toxicity][13]. After you select a template, you can modify any aspect of the evaluation.
@@ -398,18 +399,18 @@ result = triage_agent.run_sync(
[9]: https://arxiv.org/pdf/2309.11998
[10]: /security/sensitive_data_scanner/
[11]: https://app.datadoghq.com/llm/evaluations
-[12]: /llm_observability/configure/evaluations/llm_as_a_judge_evaluations/template_evaluations#sentiment
-[13]: /llm_observability/configure/evaluations/llm_as_a_judge_evaluations/template_evaluations#toxicity
-[14]: /llm_observability/configure/evaluations/llm_as_a_judge_evaluations/template_evaluations#prompt-injection
-[15]: /llm_observability/configure/evaluations/llm_as_a_judge_evaluations/template_evaluations#topic-relevancy
-[16]: /llm_observability/configure/evaluations/llm_as_a_judge_evaluations/template_evaluations#failure-to-answer
-[17]: /llm_observability/configure/evaluations/llm_as_a_judge_evaluations/
-[18]: /llm_observability/configure/evaluations/managed_evaluations/#create-new-evaluations
-[19]: /llm_observability/configure/evaluations/managed_evaluations/#edit-existing-evaluations
+[12]: /llm_observability/investigate/evaluations/llm_as_a_judge_evaluations/template_evaluations#sentiment
+[13]: /llm_observability/investigate/evaluations/llm_as_a_judge_evaluations/template_evaluations#toxicity
+[14]: /llm_observability/investigate/evaluations/llm_as_a_judge_evaluations/template_evaluations#prompt-injection
+[15]: /llm_observability/investigate/evaluations/llm_as_a_judge_evaluations/template_evaluations#topic-relevancy
+[16]: /llm_observability/investigate/evaluations/llm_as_a_judge_evaluations/template_evaluations#failure-to-answer
+[17]: /llm_observability/investigate/evaluations/llm_as_a_judge_evaluations/
+[18]: /llm_observability/investigate/evaluations/managed_evaluations/#create-new-evaluations
+[19]: /llm_observability/investigate/evaluations/managed_evaluations/#edit-existing-evaluations
[20]: https://github.com/DataDog/llm-observability/blob/main/evaluation_examples/1-tool-selection-demo.py
[21]: https://github.com/DataDog/llm-observability/blob/main/evaluation_examples/2-tool-argument-correctness-demo.py
-[22]: /llm_observability/configure/evaluations/llm_as_a_judge_evaluations/template_evaluations#goal-completeness
-[23]: /llm_observability/configure/evaluations/llm_as_a_judge_evaluations/template_evaluations#tool-argument-correctness
-[24]: /llm_observability/configure/evaluations/llm_as_a_judge_evaluations/template_evaluations#tool-selection
-[25]: /llm_observability/configure/evaluations/llm_as_a_judge_evaluations/template_evaluations#hallucination
+[22]: /llm_observability/investigate/evaluations/llm_as_a_judge_evaluations/template_evaluations#goal-completeness
+[23]: /llm_observability/investigate/evaluations/llm_as_a_judge_evaluations/template_evaluations#tool-argument-correctness
+[24]: /llm_observability/investigate/evaluations/llm_as_a_judge_evaluations/template_evaluations#tool-selection
+[25]: /llm_observability/investigate/evaluations/llm_as_a_judge_evaluations/template_evaluations#hallucination
[26]: /llm_observability/instrument/sdk?tab=python#prompt-tracking
diff --git a/hugo/content/en/llm_observability/configure/evaluations/llm_as_a_judge_evaluations/trace_level_evaluations.md b/hugo/content/en/llm_observability/investigate/evaluations/llm_as_a_judge_evaluations/trace_level_evaluations.md
similarity index 95%
rename from hugo/content/en/llm_observability/configure/evaluations/llm_as_a_judge_evaluations/trace_level_evaluations.md
rename to hugo/content/en/llm_observability/investigate/evaluations/llm_as_a_judge_evaluations/trace_level_evaluations.md
index 5b10c0b00f8..d378c4772f7 100644
--- a/hugo/content/en/llm_observability/configure/evaluations/llm_as_a_judge_evaluations/trace_level_evaluations.md
+++ b/hugo/content/en/llm_observability/investigate/evaluations/llm_as_a_judge_evaluations/trace_level_evaluations.md
@@ -2,12 +2,13 @@
title: Trace-Level Evaluations
aliases:
- /llm_observability/evaluations/custom_llm_as_a_judge_evaluations/trace_level_evaluations/
+- /llm_observability/configure/evaluations/llm_as_a_judge_evaluations/trace_level_evaluations/
description: Run a custom LLM-as-a-judge across an entire trace, with examples of when to use trace scope over span scope.
further_reading:
-- link: "/llm_observability/configure/evaluations/llm_as_a_judge_evaluations"
+- link: "/llm_observability/investigate/evaluations/llm_as_a_judge_evaluations"
tag: "Documentation"
text: "Custom LLM-as-a-Judge Evaluations"
-- link: "/llm_observability/configure/evaluations/llm_as_a_judge_evaluations/prompt_templating"
+- link: "/llm_observability/investigate/evaluations/llm_as_a_judge_evaluations/prompt_templating"
tag: "Documentation"
text: "Prompt Templating"
- link: "/llm_observability/quickstart/terms/"
@@ -221,10 +222,10 @@ Configuring evaluations requires the `Agent Observability Write` [permission][4]
{{< partial name="whats-next/whats-next.html" >}}
[1]: https://app.datadoghq.com/llm/evaluations
-[2]: /llm_observability/configure/evaluations/llm_as_a_judge_evaluations/template_evaluations
-[3]: /llm_observability/configure/evaluations/llm_as_a_judge_evaluations/prompt_templating
+[2]: /llm_observability/investigate/evaluations/llm_as_a_judge_evaluations/template_evaluations
+[3]: /llm_observability/investigate/evaluations/llm_as_a_judge_evaluations/prompt_templating
[4]: /account_management/rbac/permissions/#llm-observability
-[5]: /llm_observability/configure/evaluations/llm_as_a_judge_evaluations/#define-the-evaluation-output
+[5]: /llm_observability/investigate/evaluations/llm_as_a_judge_evaluations/#define-the-evaluation-output
[6]: /events/explorer/facets/
[7]: /monitors/
[8]: /llm_observability/investigate/annotation_queues
diff --git a/hugo/content/en/llm_observability/configure/evaluations/managed_evaluations/_index.md b/hugo/content/en/llm_observability/investigate/evaluations/managed_evaluations/_index.md
similarity index 87%
rename from hugo/content/en/llm_observability/configure/evaluations/managed_evaluations/_index.md
rename to hugo/content/en/llm_observability/investigate/evaluations/managed_evaluations/_index.md
index 4311889fe6c..e17fc8958e1 100644
--- a/hugo/content/en/llm_observability/configure/evaluations/managed_evaluations/_index.md
+++ b/hugo/content/en/llm_observability/investigate/evaluations/managed_evaluations/_index.md
@@ -15,6 +15,7 @@ aliases:
- /llm_observability/evaluations/ootb_evaluations
- /llm_observability/configure/evaluations/ootb_evaluations
- /llm_observability/evaluations/managed_evaluations/
+ - /llm_observability/configure/evaluations/managed_evaluations/
---
## Overview
@@ -48,6 +49,6 @@ After you click {{< ui >}}Save and Publish{{< /ui >}}, the evaluation goes live.
{{< partial name="whats-next/whats-next.html" >}}
[1]: https://app.datadoghq.com/llm/evaluations
-[2]: /llm_observability/configure/evaluations/compatibility
-[3]: /llm_observability/configure/evaluations/managed_evaluations/quality_evaluations#language-mismatch
-[4]: /llm_observability/configure/evaluations/managed_evaluations/security_and_safety_evaluations#sensitive-data-scanning
+[2]: /llm_observability/investigate/evaluations/compatibility
+[3]: /llm_observability/investigate/evaluations/language_mismatch
+[4]: /llm_observability/investigate/evaluations/managed_evaluations/security_and_safety_evaluations
diff --git a/hugo/content/en/llm_observability/configure/evaluations/managed_evaluations/security_and_safety_evaluations.md b/hugo/content/en/llm_observability/investigate/evaluations/managed_evaluations/security_and_safety_evaluations.md
similarity index 93%
rename from hugo/content/en/llm_observability/configure/evaluations/managed_evaluations/security_and_safety_evaluations.md
rename to hugo/content/en/llm_observability/investigate/evaluations/managed_evaluations/security_and_safety_evaluations.md
index 93c3daf3041..e291a2b2b2e 100644
--- a/hugo/content/en/llm_observability/configure/evaluations/managed_evaluations/security_and_safety_evaluations.md
+++ b/hugo/content/en/llm_observability/investigate/evaluations/managed_evaluations/security_and_safety_evaluations.md
@@ -12,6 +12,7 @@ aliases:
- /llm_observability/evaluations/sensitive_data_scanner
- /llm_observability/configure/evaluations/sensitive_data_scanner
- /llm_observability/evaluations/managed_evaluations/security_and_safety_evaluations/
+ - /llm_observability/configure/evaluations/managed_evaluations/security_and_safety_evaluations/
---
This check ensures that sensitive information is handled appropriately and securely, reducing the risk of data breaches or unauthorized access.
diff --git a/hugo/content/en/llm_observability/investigate/metrics.md b/hugo/content/en/llm_observability/investigate/metrics.md
index be998a0ec7e..e223e31bb7b 100644
--- a/hugo/content/en/llm_observability/investigate/metrics.md
+++ b/hugo/content/en/llm_observability/investigate/metrics.md
@@ -26,7 +26,7 @@ The ml_obs.* entries on this page are Datadog M
They are distinct from two other things in Agent Observability:
- Per-span operational data (cost, tokens, latency, errors on each individual trace or span): the raw values these metrics roll up from. Stored with spans, follow Agent Observability trace retention, and are queried from the Traces explorer rather than as metrics.
-- Evaluation scores (also called "evals"): quality and safety judgments (for example, hallucination, faithfulness, custom LLM-as-a-judge) attached to individual spans or experiment rows. These are not derived from operational telemetry, and follow Agent Observability trace and experiment retention rather than Datadog metric retention.
+- Evaluation scores (also called "evals"): quality and safety judgments (for example, hallucination, faithfulness, custom LLM-as-a-judge) attached to individual spans or experiment rows. These are not derived from operational telemetry, and follow Agent Observability trace and experiment retention rather than Datadog metric retention.
diff --git a/hugo/content/en/llm_observability/investigate/patterns.md b/hugo/content/en/llm_observability/investigate/patterns.md
index c5283cf5bc4..6976671f831 100644
--- a/hugo/content/en/llm_observability/investigate/patterns.md
+++ b/hugo/content/en/llm_observability/investigate/patterns.md
@@ -168,7 +168,7 @@ Re-run your Pattern periodically and use the {{< ui >}}Compare to{{< /ui >}} dro
{{< partial name="whats-next/whats-next.html" >}}
-[1]: /llm_observability/configure/evaluations/llm_as_a_judge_evaluations/connect_to_account/
+[1]: /llm_observability/investigate/evaluations/llm_as_a_judge_evaluations/connect_to_account/
[2]: /llm_observability/improve/datasets/
[3]: /llm_observability/investigate/annotation_queues/
[4]: https://app.datadoghq.com/llm/patterns
diff --git a/hugo/content/en/llm_observability/investigate/querying.md b/hugo/content/en/llm_observability/investigate/querying.md
index 1451355e43d..d2c83705684 100644
--- a/hugo/content/en/llm_observability/investigate/querying.md
+++ b/hugo/content/en/llm_observability/investigate/querying.md
@@ -139,9 +139,9 @@ Use the `@trace` attribute to access trace-level information, such as estimated
[1]: https://app.datadoghq.com/llm/traces
[2]: /llm_observability/quickstart/terms/
-[3]: /llm_observability/configure/evaluations/
-[4]: /llm_observability/configure/evaluations/submit_evaluations
+[3]: /llm_observability/investigate/evaluations/
+[4]: /llm_observability/investigate/evaluations/external_evaluations
[5]: /llm_observability/quickstart/terms/#span-kinds
[6]: /tracing/trace_explorer/query_syntax/
[7]: /llm_observability/instrument/sdk/#annotating-metadata
-[8]: /llm_observability/configure/evaluations/end_user_feedback
+[8]: /llm_observability/investigate/evaluations/end_user_feedback
diff --git a/hugo/content/en/llm_observability/quickstart/_index.md b/hugo/content/en/llm_observability/quickstart/_index.md
index 31dd0bb9d5b..52018057193 100644
--- a/hugo/content/en/llm_observability/quickstart/_index.md
+++ b/hugo/content/en/llm_observability/quickstart/_index.md
@@ -16,7 +16,7 @@ further_reading:
- link: '/llm_observability/instrument/otel_instrumentation'
tag: 'Documentation'
text: 'Instrument with OpenTelemetry'
- - link: '/llm_observability/configure/evaluations'
+ - link: '/llm_observability/investigate/evaluations'
tag: 'Evaluations'
text: 'Configure Evaluations on your application'
- link: '/llm_observability/lapdog'
@@ -236,7 +236,7 @@ To try Agent Observability locally, for free, [follow the steps][12] to instrume
{{< partial name="whats-next/whats-next.html" >}}
[3]: https://app.datadoghq.com/llm/traces
-[4]: /llm_observability/configure/evaluations
+[4]: /llm_observability/investigate/evaluations
[5]: /llm_observability/instrument/sdk#manual-instrumentation
[6]: /llm_observability/instrument/auto_instrumentation
[7]: /llm_observability/instrument/auto_instrumentation/?tab=python
diff --git a/hugo/content/en/llm_observability/quickstart/terms/_index.md b/hugo/content/en/llm_observability/quickstart/terms/_index.md
index 726344e8e47..8c294bf146e 100644
--- a/hugo/content/en/llm_observability/quickstart/terms/_index.md
+++ b/hugo/content/en/llm_observability/quickstart/terms/_index.md
@@ -11,7 +11,7 @@ further_reading:
- link: '/llm_observability/setup'
tag: 'Documentation'
text: 'Learn how to set up Agent Observability'
- - link: '/llm_observability/configure/evaluations'
+ - link: '/llm_observability/investigate/evaluations'
tag: 'Guide'
text: 'Evaluation options for Agent Observability'
---
@@ -171,11 +171,11 @@ In addition, Datadog's [Sensitive Data Scanner][5] is natively integrated with A
[3]: /llm_observability/setup/auto_instrumentation/
[4]: /llm_observability/setup/?tab=decorators#instrument-your-llm-application
[5]: /security/sensitive_data_scanner/
-[6]: /llm_observability/configure/evaluations/submit_evaluations
+[6]: /llm_observability/investigate/evaluations/external_evaluations
[7]: https://github.com/DataDog/llm-observability/blob/main/1-llm-span.ipynb
[8]: https://github.com/DataDog/llm-observability/blob/main/2-workflow-span.ipynb
[9]: https://github.com/DataDog/llm-observability/blob/main/3-agent-span.ipynb
[10]: https://github.com/DataDog/llm-observability/blob/main/4-custom-evaluations.ipynb
-[11]: /llm_observability/configure/evaluations/
-[12]: /llm_observability/configure/evaluations/managed_evaluations
-[13]: /llm_observability/configure/evaluations/external_evaluations/nemo
+[11]: /llm_observability/investigate/evaluations/
+[12]: /llm_observability/investigate/evaluations/managed_evaluations
+[13]: /llm_observability/investigate/evaluations/external_evaluations/nemo