Move LLM evaluation docs to Investigate

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

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

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

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 >}}

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 >}}

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
 

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
 
-<div class="alert alert-info">For comprehensive examples and guidance on building custom evaluators, see the <a href="/llm_observability/guide/evaluation_developer_guide/">Evaluation Developer Guide</a>.</div>
+<div class="alert alert-info">For comprehensive examples and guidance on building custom evaluators, see the <a href="/llm_observability/investigate/evaluations/evaluation_developer_guide/">Evaluation Developer Guide</a>.</div>
 
 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

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

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": "<role>", "content": "<template string with placeholders>" }` 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<string, string>): 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": "<role>", "content": "<template string with placeholders>" }` objects.
 - `tags` (Record<string, string>): 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.
 
-<div class="alert alert-info">For building reusable, class-based evaluators (<code>BaseEvaluator</code>, <code>BaseSummaryEvaluator</code>) with rich result metadata, see the <a href="/llm_observability/guide/evaluation_developer_guide/">Evaluation Developer Guide</a>.</div>
+<div class="alert alert-info">For building reusable, class-based evaluators (<code>BaseEvaluator</code>, <code>BaseSummaryEvaluator</code>) with rich result metadata, see the <a href="/llm_observability/investigate/evaluations/evaluation_developer_guide/">Evaluation Developer Guide</a>.</div>
 
 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.

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

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

hugo/content/en/llm_observability/configure/evaluations/_index.md → 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