diff --git a/website/docs/tutorials/observability/observability.md b/website/docs/tutorials/observability/metrics.md
similarity index 99%
rename from website/docs/tutorials/observability/observability.md
rename to website/docs/tutorials/observability/metrics.md
index af523e6d..913d662b 100644
--- a/website/docs/tutorials/observability/observability.md
+++ b/website/docs/tutorials/observability/metrics.md
@@ -1,4 +1,4 @@
-# Observability
+# Metrics & Monitoring
 
 Metrics collection and visualization for Semantic Router using Prometheus and Grafana.
 
diff --git a/website/docs/tutorials/observability/tracing-quickstart.md b/website/docs/tutorials/observability/tracing-quickstart.md
deleted file mode 100644
index ffe88586..00000000
--- a/website/docs/tutorials/observability/tracing-quickstart.md
+++ /dev/null
@@ -1,115 +0,0 @@
-# Quick Start: Distributed Tracing
-
-Get started with distributed tracing in 5 minutes.
-
-## Step 1: Enable Tracing
-
-Edit your `config.yaml`:
-
-```yaml
-observability:
-  tracing:
-    enabled: true
-    provider: "opentelemetry"
-    exporter:
-      type: "stdout"
-    sampling:
-      type: "always_on"
-    resource:
-      service_name: "vllm-semantic-router"
-      deployment_environment: "development"
-```
-
-## Step 2: Start the Router
-
-```bash
-./semantic-router --config config.yaml
-```
-
-## Step 3: Send a Test Request
-
-```bash
-curl -X POST http://localhost:8080/v1/chat/completions \
-  -H "Content-Type: application/json" \
-  -d '{
-    "model": "auto",
-    "messages": [{"role": "user", "content": "What is 2+2?"}]
-  }'
-```
-
-## Step 4: View Traces
-
-Check your console output for JSON trace spans:
-
-```json
-{
-  "Name": "semantic_router.request.received",
-  "Attributes": [
-    {"Key": "request.id", "Value": "req-123"},
-    {"Key": "http.method", "Value": "POST"}
-  ]
-}
-```
-
-## What's Next?
-
-### Production Deployment with Jaeger
-
-1. **Start Jaeger**:
-
-   ```bash
-   docker run -d -p 4317:4317 -p 16686:16686 \
-     jaegertracing/all-in-one:latest
-   ```
-
-2. **Update config.yaml**:
-
-   ```yaml
-   observability:
-     tracing:
-       enabled: true
-       exporter:
-         type: "otlp"
-         endpoint: "localhost:4317"
-         insecure: true
-       sampling:
-         type: "probabilistic"
-         rate: 0.1
-   ```
-
-3. **View traces**: http://localhost:16686
-
-### Key Metrics to Monitor
-
-- **Classification Time**: `classification.time_ms` attribute
-- **Cache Hit Rate**: Filter by `cache.hit = true`
-- **Security Blocks**: Filter by `security.action = blocked`
-- **Routing Decisions**: `routing.strategy` and `routing.reason` attributes
-
-### Common Use Cases
-
-**Find slow requests:**
-
-```
-Min Duration: 1s
-Service: vllm-semantic-router
-```
-
-**Debug specific request:**
-
-```
-Tags: request.id = req-abc-123
-```
-
-**Analyze classification performance:**
-
-```
-Operation: semantic_router.classification
-Sort by: Duration (desc)
-```
-
-## Learn More
-
-- [Full Distributed Tracing Guide](./distributed-tracing.md)
-- [Configuration Reference](../../installation/configuration.md)
-- [Observability Overview](./observability.md)
diff --git a/website/docs/tutorials/semantic-cache/in-memory-cache.md b/website/docs/tutorials/semantic-cache/in-memory-cache.md
index 2bc2291c..e06d02ea 100644
--- a/website/docs/tutorials/semantic-cache/in-memory-cache.md
+++ b/website/docs/tutorials/semantic-cache/in-memory-cache.md
@@ -162,4 +162,4 @@ The in-memory cache automatically manages memory through:
 
 - **[Milvus Cache](./milvus-cache.md)** - Set up persistent, distributed caching
 - **[Cache Overview](./overview.md)** - Learn about semantic caching concepts
-- **[Observability](../observability/observability.md)** - Monitor cache performance
+- **[Observability](../observability/overview.md)** - Monitor cache performance
diff --git a/website/docs/tutorials/semantic-cache/milvus-cache.md b/website/docs/tutorials/semantic-cache/milvus-cache.md
index d6ea9c57..5b1ff7cf 100644
--- a/website/docs/tutorials/semantic-cache/milvus-cache.md
+++ b/website/docs/tutorials/semantic-cache/milvus-cache.md
@@ -145,5 +145,5 @@ curl -X POST http://localhost:8080/v1/chat/completions \
 ## Next Steps
 
 - **[In-Memory Cache](./in-memory-cache.md)** - Compare with in-memory caching
-- **[Cache Overview](./overview.md)** - Learn semantic caching concepts  
-- **[Observability](../observability/observability.md)** - Monitor Milvus performance
+- **[Cache Overview](./overview.md)** - Learn semantic caching concepts
+- **[Observability](../observability/overview.md)** - Monitor Milvus performance
diff --git a/website/sidebars.ts b/website/sidebars.ts
index a67f9670..67229a71 100644
--- a/website/sidebars.ts
+++ b/website/sidebars.ts
@@ -87,7 +87,9 @@ const sidebars: SidebarsConfig = {
           label: 'Observability',
           items: [
             'tutorials/observability/overview',
-            'tutorials/observability/observability',
+            'tutorials/observability/metrics',
+            'tutorials/observability/distributed-tracing',
+            'tutorials/observability/open-webui-integration',
           ],
         },
       ],