DOCS-8441 LLM Observability Documentation Navigation Update

config/_default/menus/main.en.yaml

@@ -3718,49 +3718,49 @@ menu:
     - name: LLM Observability
       url: llm_observability/
       pre: llm-observability
-      identifier: llm_observability
+      identifier: llm_obs
       parent: ai_observability_heading
       weight: 10000
-    - name: Core Concepts
-      url: llm_observability/core_concepts/
-      parent: llm_observability
-      identifier: tracing_llm_obs_core_concepts
-      weight: 1
     - name: Quickstart
       url: llm_observability/quickstart/
-      parent: llm_observability
-      identifier: tracing_llm_obs_quickstart
+      parent: llm_obs
+      identifier: llm_obs_quickstart
+      weight: 1
+    - name: Terms and Concepts
+      url: llm_observability/terms/
+      parent: llm_obs
+      identifier: llm_obs_terms
       weight: 2
-    - name: Trace an LLM Application
-      url: llm_observability/trace_an_llm_application/
-      parent: llm_observability
-      identifier: tracing_llm_obs_trace_an_application
+    - name: Setup
+      url: llm_observability/setup/
+      parent: llm_obs
+      identifier: llm_obs_setup
       weight: 3
-    - name: Span Kinds
-      url: llm_observability/span_kinds/
-      parent: llm_observability
-      identifier: tracing_llm_obs_span_kinds
-      weight: 4
-    - name: Auto Instrumentation
-      url: llm_observability/auto_instrumentation/
-      parent: llm_observability
-      identifier: tracing_llm_obs_auto_instrumentation
-      weight: 5
     - name: SDK
-      url: llm_observability/sdk/
-      parent: llm_observability
-      identifier: tracing_llm_obs_sdk
-      weight: 6
+      url: llm_observability/setup/sdk/
+      parent: llm_obs_setup
+      identifier: llm_obs_setup_sdk
+      weight: 301
+    - name: Auto Instrumentation
+      url: llm_observability/setup/auto_instrumentation
+      parent: llm_obs_setup
+      identifier: llm_obs_setup_auto_instrumentation
+      weight: 302
     - name: API
-      url: llm_observability/api/
-      parent: llm_observability
-      identifier: tracing_llm_obs_api
-      weight: 7
+      url: llm_observability/setup/api/
+      parent: llm_obs_setup
+      identifier: llm_obs_setup_api
+      weight: 303
     - name: Submit Evaluations
       url: llm_observability/submit_evaluations/
-      parent: llm_observability
-      identifier: tracing_llm_obs_submit_evaluations
-      weight: 8
+      parent: llm_obs
+      identifier: llm_obs_submit_evaluations
+      weight: 4
+    - name: Guides
+      url: llm_observability/guide/
+      parent: llm_obs
+      identifier: llm_obs_guide
+      weight: 5
     - name: CI Visibility
       url: continuous_integration/
       pre: ci

content/en/llm_observability/_index.md

@@ -17,56 +17,55 @@ LLM Observability is not available in the US1-FED site.
 
 ## Overview
 
-{{< img src="llm_observability/llm-observability-landing.png" alt="LLM Observability overview page with record of all prompt-response pair traces" style="width:100%;" >}}
-
 With LLM Observability, you can monitor, troubleshoot, and evaluate your LLM-powered applications, such as chatbots. You can investigate the root cause of issues, monitor operational performance, and evaluate the quality, privacy, and safety of your LLM applications. 
 
-Each request fulfilled by your application is represented as a trace on the [LLM Observability traces page][2] in Datadog. A trace can represent:
+Each request fulfilled by your application is represented as a trace on the [**LLM Observability** page][1] in Datadog. A trace can represent:
+
 - An individual LLM inference, including tokens, error information, and latency
 - A predetermined LLM workflow, which is a grouping of LLM calls and their contextual operations, such as tool calls or preprocessing steps
 - A dynamic LLM workflow executed by an LLM agent
 
-Each trace contains spans representing each choice made by an agent or each step of a given workflow. A given trace can also include input and output, latency, privacy issues, errors, and more.
-
-You can instrument your application with the LLM Observability SDK for Python, or by calling the LLM Observability API.
-
-## Getting started
-
-To get started with LLM Observability, you can build a simple example with the [Quickstart][3], or follow [the guide for instrumenting your LLM application][4].
+{{< img src="llm_observability/llm-observability-landing.png" alt="LLM Observability overview page with record of all prompt-response pair traces" style="width:100%;" >}}
 
-## Explore LLM Observability
+Each trace contains spans representing each choice made by an agent or each step of a given workflow. A given trace can also include input and output, latency, privacy issues, errors, and more. For more information, see [Terms and Concepts][2].
 
-### Troubleshoot with end-to-end tracing
+## Troubleshoot with end-to-end tracing
 
 View every step of your LLM application chains and calls to pinpoint problematic requests and identify the root cause of errors.
 
 {{< img src="llm_observability/llm-observability-overview.png" alt="An LLM Observability trace displaying each span of a request" style="width:100%;" >}}
 
-### Monitor operational metrics and optimize cost
+## Monitor operational metrics and optimize cost
 
 Monitor the throughput, latency, and token usage trends for all your LLM applications.
 
 {{< img src="llm_observability/dashboard.png" alt="The out-of-the-box LLM Observability dashboard" style="width:100%;" >}}
 
-### Evaluate the quality and effectiveness of your LLM applications
+## Evaluate the quality and effectiveness of your LLM applications
 
 Identify problematic clusters and monitor the quality of responses over time with topical clustering and checks like sentiment, failure to answer, and so on.
 
 {{< img src="llm_observability/clusters-page.png" alt="The clusters page in LLM Observability" style="width:100%;" >}}
 
-### Safeguard sensitive data and identify malicious users
+## Safeguard sensitive data and identify malicious users
 
 Automatically scan and redact any sensitive data in your AI applications and identify prompt injections.
 
 {{< img src="llm_observability/prompt-injection.png" alt="An example of a prompt-injection attempt" style="width:100%;" >}}
 
 By using LLM Observability, you acknowledge that Datadog is authorized to share your Company's data with OpenAI LLC for the purpose of providing and improving LLM Observability. OpenAI will not use your data for training or tuning purposes. If you have any questions or want to opt out of features that depend on OpenAI, reach out to your account representative.
 
-## Further reading
+## Ready to start?
+
+See the [Setup documentation][5] for instructions on instrumenting your LLM application or follow the [Trace an LLM Application guide][6] to generate a trace using the [LLM Observability SDK for Python][3].
+
+## Further Reading
 
 {{< partial name="whats-next/whats-next.html" >}}
 
-[1]: /llm_observability/spans/
-[2]: https://app.datadoghq.com/llm/traces
-[3]: /llm_observability/quickstart
-[4]: /llm_observability/trace_an_llm_application
+[1]: https://app.datadoghq.com/llm/traces
+[2]: /llm_observability/terms
+[3]: /llm_observability/setup/sdk
+[4]: /llm_observability/setup/api
+[5]: /llm_observability/setup
+[6]: /llm_observability/quickstart

content/en/llm_observability/guide/_index.md

@@ -0,0 +1,15 @@
+---
+title: LLM Observability Guides
+private: true
+disable_toc: true
+cascade:
+    algolia:
+        rank: 20
+        category: Guide
+        subcategory: LLM Observability Guides
+---
+
+{{< whatsnext desc="LLM Observability Guides:" >}}
+    {{< nextlink href="/llm_observability/quickstart" >}}Trace an LLM Application{{< /nextlink >}}
+    {{< nextlink href="/llm_observability/submit_evaluations" >}}Submit Evaluations{{< /nextlink >}}
+{{< /whatsnext >}}