diff --git a/arch/envoy.template.yaml b/arch/envoy.template.yaml
index 4c716e3a..14e26e84 100644
--- a/arch/envoy.template.yaml
+++ b/arch/envoy.template.yaml
@@ -115,26 +115,20 @@ static_resources:
                       domains:
                         - "*"
                       routes:
+
+                        {% for internal_clustrer in ["embeddings", "zeroshot", "guard", "arch_fc", "hallucination"] %}
                         - match:
                             prefix: "/"
                             headers:
                               - name: "x-arch-upstream"
                                 string_match:
-                                  exact: model_server
+                                  exact: {{ internal_clustrer }}
                           route:
                             auto_host_rewrite: true
-                            cluster: model_server
-                            timeout: 60s
-                        - match:
-                            prefix: "/"
-                            headers:
-                              - name: "x-arch-upstream"
-                                string_match:
-                                  exact: arch_fc
-                          route:
-                            auto_host_rewrite: true
-                            cluster: model_server
+                            cluster: {{ internal_clustrer }}
                             timeout: 60s
+                        {% endfor %}
+
                         {% for _, cluster in arch_clusters.items() %}
                         - match:
                             prefix: "/"
@@ -278,13 +272,14 @@ static_resources:
         typed_config:
           "@type": type.googleapis.com/envoy.extensions.transport_sockets.tls.v3.UpstreamTlsContext
           sni: api.mistral.ai
-    - name: model_server
+    {% for internal_clustrer in ["embeddings", "zeroshot", "guard", "arch_fc", "hallucination"] %}
+    - name: {{ internal_clustrer }}
       connect_timeout: 5s
       type: STRICT_DNS
       dns_lookup_family: V4_ONLY
       lb_policy: ROUND_ROBIN
       load_assignment:
-        cluster_name: model_server
+        cluster_name: {{ internal_clustrer }}
         endpoints:
           - lb_endpoints:
               - endpoint:
@@ -292,7 +287,8 @@ static_resources:
                     socket_address:
                       address: host.docker.internal
                       port_value: 51000
-                  hostname: "model_server"
+                  hostname: {{ internal_clustrer }}
+    {% endfor %}
     - name: mistral_7b_instruct
       connect_timeout: 5s
       type: STRICT_DNS
@@ -308,21 +304,6 @@ static_resources:
                       address: mistral_7b_instruct
                       port_value: 10001
                   hostname: "mistral_7b_instruct"
-    - name: arch_fc
-      connect_timeout: 5s
-      type: STRICT_DNS
-      dns_lookup_family: V4_ONLY
-      lb_policy: ROUND_ROBIN
-      load_assignment:
-        cluster_name: arch_fc
-        endpoints:
-          - lb_endpoints:
-              - endpoint:
-                  address:
-                    socket_address:
-                      address: host.docker.internal
-                      port_value: 51000
-                  hostname: "arch_fc"
 {% for _, cluster in arch_clusters.items() %}
     - name: {{ cluster.name }}
       {% if cluster.connect_timeout -%}
diff --git a/crates/common/src/consts.rs b/crates/common/src/consts.rs
index fdc21aed..fe67f6a8 100644
--- a/crates/common/src/consts.rs
+++ b/crates/common/src/consts.rs
@@ -8,9 +8,13 @@ pub const USER_ROLE: &str = "user";
 pub const TOOL_ROLE: &str = "tool";
 pub const ASSISTANT_ROLE: &str = "assistant";
 pub const GPT_35_TURBO: &str = "gpt-3.5-turbo";
-pub const ARC_FC_CLUSTER: &str = "arch_fc";
 pub const ARCH_FC_REQUEST_TIMEOUT_MS: u64 = 120000; // 2 minutes
 pub const MODEL_SERVER_NAME: &str = "model_server";
+pub const ZEROSHOT_INTERNAL_HOST: &str = "zeroshot";
+pub const ARCH_FC_INTERNAL_HOST: &str = "arch_fc";
+pub const HALLUCINATION_INTERNAL_HOST: &str = "hallucination";
+pub const EMBEDDINGS_INTERNAL_HOST: &str = "embeddings";
+pub const GUARD_INTERNAL_HOST: &str = "guard";
 pub const ARCH_ROUTING_HEADER: &str = "x-arch-llm-provider";
 pub const ARCH_MESSAGES_KEY: &str = "arch_messages";
 pub const ARCH_PROVIDER_HINT_HEADER: &str = "x-arch-llm-provider-hint";
diff --git a/crates/prompt_gateway/src/filter_context.rs b/crates/prompt_gateway/src/filter_context.rs
index 655b391f..b60191a5 100644
--- a/crates/prompt_gateway/src/filter_context.rs
+++ b/crates/prompt_gateway/src/filter_context.rs
@@ -1,10 +1,9 @@
 use crate::stream_context::StreamContext;
 use common::common_types::EmbeddingType;
+use common::consts::{ARCH_INTERNAL_CLUSTER_NAME, EMBEDDINGS_INTERNAL_HOST};
 use common::configuration::{Configuration, Overrides, PromptGuards, PromptTarget};
-use common::consts::ARCH_INTERNAL_CLUSTER_NAME;
 use common::consts::ARCH_UPSTREAM_HOST_HEADER;
 use common::consts::DEFAULT_EMBEDDING_MODEL;
-use common::consts::MODEL_SERVER_NAME;
 use common::embeddings::{
     CreateEmbeddingRequest, CreateEmbeddingRequestInput, CreateEmbeddingResponse,
 };
@@ -100,10 +99,10 @@ impl FilterContext {
             ARCH_INTERNAL_CLUSTER_NAME,
             "/embeddings",
             vec![
-                (ARCH_UPSTREAM_HOST_HEADER, MODEL_SERVER_NAME),
+                (ARCH_UPSTREAM_HOST_HEADER, EMBEDDINGS_INTERNAL_HOST),
                 (":method", "POST"),
                 (":path", "/embeddings"),
-                (":authority", MODEL_SERVER_NAME),
+                (":authority", EMBEDDINGS_INTERNAL_HOST),
                 ("content-type", "application/json"),
                 ("x-envoy-upstream-rq-timeout-ms", "60000"),
             ],
diff --git a/crates/prompt_gateway/src/stream_context.rs b/crates/prompt_gateway/src/stream_context.rs
index 18463b49..33938deb 100644
--- a/crates/prompt_gateway/src/stream_context.rs
+++ b/crates/prompt_gateway/src/stream_context.rs
@@ -12,11 +12,7 @@ use common::common_types::{
 };
 use common::configuration::{Overrides, PromptGuards, PromptTarget};
 use common::consts::{
-    ARCH_FC_MODEL_NAME, ARCH_FC_REQUEST_TIMEOUT_MS, ARCH_INTERNAL_CLUSTER_NAME, ARCH_MESSAGES_KEY,
-    ARCH_MODEL_PREFIX, ARCH_STATE_HEADER, ARCH_UPSTREAM_HOST_HEADER, ARC_FC_CLUSTER,
-    ASSISTANT_ROLE, CHAT_COMPLETIONS_PATH, DEFAULT_EMBEDDING_MODEL, DEFAULT_HALLUCINATED_THRESHOLD,
-    DEFAULT_INTENT_MODEL, DEFAULT_PROMPT_TARGET_THRESHOLD, GPT_35_TURBO, MODEL_SERVER_NAME,
-    REQUEST_ID_HEADER, SYSTEM_ROLE, TOOL_ROLE, USER_ROLE,
+    ARCH_FC_INTERNAL_HOST, ARCH_FC_MODEL_NAME, ARCH_FC_REQUEST_TIMEOUT_MS, ARCH_INTERNAL_CLUSTER_NAME, ARCH_MESSAGES_KEY, ARCH_MODEL_PREFIX, ARCH_STATE_HEADER, ARCH_UPSTREAM_HOST_HEADER, ASSISTANT_ROLE, CHAT_COMPLETIONS_PATH, DEFAULT_EMBEDDING_MODEL, DEFAULT_HALLUCINATED_THRESHOLD, DEFAULT_INTENT_MODEL, DEFAULT_PROMPT_TARGET_THRESHOLD, EMBEDDINGS_INTERNAL_HOST, GPT_35_TURBO, GUARD_INTERNAL_HOST, HALLUCINATION_INTERNAL_HOST, REQUEST_ID_HEADER, SYSTEM_ROLE, TOOL_ROLE, USER_ROLE, ZEROSHOT_INTERNAL_HOST
 };
 use common::embeddings::{
     CreateEmbeddingRequest, CreateEmbeddingRequestInput, CreateEmbeddingResponse,
@@ -244,10 +240,10 @@ impl StreamContext {
         };
 
         let mut headers = vec![
-            (ARCH_UPSTREAM_HOST_HEADER, MODEL_SERVER_NAME),
+            (ARCH_UPSTREAM_HOST_HEADER, ZEROSHOT_INTERNAL_HOST),
             (":method", "POST"),
             (":path", "/zeroshot"),
-            (":authority", MODEL_SERVER_NAME),
+            (":authority", ZEROSHOT_INTERNAL_HOST),
             ("content-type", "application/json"),
             ("x-envoy-max-retries", "3"),
             ("x-envoy-upstream-rq-timeout-ms", "60000"),
@@ -557,9 +553,9 @@ impl StreamContext {
 
         let mut headers = vec![
             (":method", "POST"),
-            (ARCH_UPSTREAM_HOST_HEADER, ARC_FC_CLUSTER),
+            (ARCH_UPSTREAM_HOST_HEADER, ARCH_FC_INTERNAL_HOST),
             (":path", "/v1/chat/completions"),
-            (":authority", ARC_FC_CLUSTER),
+            (":authority", ARCH_FC_INTERNAL_HOST),
             ("content-type", "application/json"),
             ("x-envoy-max-retries", "3"),
             ("x-envoy-upstream-rq-timeout-ms", timeout_str.as_str()),
@@ -713,10 +709,10 @@ impl StreamContext {
                 };
 
             let mut headers = vec![
-                (ARCH_UPSTREAM_HOST_HEADER, MODEL_SERVER_NAME),
+                (ARCH_UPSTREAM_HOST_HEADER, HALLUCINATION_INTERNAL_HOST),
                 (":method", "POST"),
                 (":path", "/hallucination"),
-                (":authority", MODEL_SERVER_NAME),
+                (":authority", HALLUCINATION_INTERNAL_HOST),
                 ("content-type", "application/json"),
                 ("x-envoy-max-retries", "3"),
                 ("x-envoy-upstream-rq-timeout-ms", "60000"),
@@ -948,10 +944,10 @@ impl StreamContext {
         };
 
         let mut headers = vec![
-            (ARCH_UPSTREAM_HOST_HEADER, MODEL_SERVER_NAME),
+            (ARCH_UPSTREAM_HOST_HEADER, EMBEDDINGS_INTERNAL_HOST),
             (":method", "POST"),
             (":path", "/embeddings"),
-            (":authority", MODEL_SERVER_NAME),
+            (":authority", EMBEDDINGS_INTERNAL_HOST),
             ("content-type", "application/json"),
             ("x-envoy-max-retries", "3"),
             ("x-envoy-upstream-rq-timeout-ms", "60000"),
@@ -1207,10 +1203,10 @@ impl HttpContext for StreamContext {
         };
 
         let mut headers = vec![
-            (ARCH_UPSTREAM_HOST_HEADER, MODEL_SERVER_NAME),
+            (ARCH_UPSTREAM_HOST_HEADER, GUARD_INTERNAL_HOST),
             (":method", "POST"),
             (":path", "/guard"),
-            (":authority", MODEL_SERVER_NAME),
+            (":authority", GUARD_INTERNAL_HOST),
             ("content-type", "application/json"),
             ("x-envoy-max-retries", "3"),
             ("x-envoy-upstream-rq-timeout-ms", "60000"),
diff --git a/crates/prompt_gateway/tests/integration.rs b/crates/prompt_gateway/tests/integration.rs
index 14ca1aa2..7f7322f8 100644
--- a/crates/prompt_gateway/tests/integration.rs
+++ b/crates/prompt_gateway/tests/integration.rs
@@ -78,10 +78,10 @@ fn normal_flow(module: &mut Tester, filter_context: i32, http_context: i32) {
         .expect_http_call(
             Some("arch_internal"),
             Some(vec![
-                ("x-arch-upstream", "model_server"),
+                ("x-arch-upstream", "guard"),
                 (":method", "POST"),
                 (":path", "/guard"),
-                (":authority", "model_server"),
+                (":authority", "guard"),
                 ("content-type", "application/json"),
                 ("x-envoy-max-retries", "3"),
                 ("x-envoy-upstream-rq-timeout-ms", "60000"),
@@ -119,10 +119,10 @@ fn normal_flow(module: &mut Tester, filter_context: i32, http_context: i32) {
         .expect_http_call(
             Some("arch_internal"),
             Some(vec![
-                ("x-arch-upstream", "model_server"),
+                ("x-arch-upstream", "embeddings"),
                 (":method", "POST"),
                 (":path", "/embeddings"),
-                (":authority", "model_server"),
+                (":authority", "embeddings"),
                 ("content-type", "application/json"),
                 ("x-envoy-max-retries", "3"),
                 ("x-envoy-upstream-rq-timeout-ms", "60000"),
@@ -164,10 +164,10 @@ fn normal_flow(module: &mut Tester, filter_context: i32, http_context: i32) {
         .expect_http_call(
             Some("arch_internal"),
             Some(vec![
-                ("x-arch-upstream", "model_server"),
+                ("x-arch-upstream", "zeroshot"),
                 (":method", "POST"),
                 (":path", "/zeroshot"),
-                (":authority", "model_server"),
+                (":authority", "zeroshot"),
                 ("content-type", "application/json"),
                 ("x-envoy-max-retries", "3"),
                 ("x-envoy-upstream-rq-timeout-ms", "60000"),
@@ -249,10 +249,10 @@ fn setup_filter(module: &mut Tester, config: &str) -> i32 {
         .expect_http_call(
             Some("arch_internal"),
             Some(vec![
-                ("x-arch-upstream", "model_server"),
+                ("x-arch-upstream", "embeddings"),
                 (":method", "POST"),
                 (":path", "/embeddings"),
-                (":authority", "model_server"),
+                (":authority", "embeddings"),
                 ("content-type", "application/json"),
                 ("x-envoy-upstream-rq-timeout-ms", "60000"),
             ]),
@@ -568,10 +568,10 @@ fn request_to_llm_gateway() {
         .expect_http_call(
             Some("arch_internal"),
             Some(vec![
-                ("x-arch-upstream", "model_server"),
+                ("x-arch-upstream", "hallucination"),
                 (":method", "POST"),
                 (":path", "/hallucination"),
-                (":authority", "model_server"),
+                (":authority", "hallucination"),
                 ("content-type", "application/json"),
                 ("x-envoy-max-retries", "3"),
                 ("x-envoy-upstream-rq-timeout-ms", "60000"),
diff --git a/demos/function_calling/grafana/dashboards/envoy_overview.json b/demos/function_calling/grafana/dashboards/envoy_overview.json
index eca35419..3bb43a91 100644
--- a/demos/function_calling/grafana/dashboards/envoy_overview.json
+++ b/demos/function_calling/grafana/dashboards/envoy_overview.json
@@ -39,8 +39,8 @@
             "axisPlacement": "auto",
             "barAlignment": 0,
             "barWidthFactor": 0.6,
-            "drawStyle": "line",
-            "fillOpacity": 0,
+            "drawStyle": "bars",
+            "fillOpacity": 54,
             "gradientMode": "none",
             "hideFrom": {
               "legend": false,
@@ -58,7 +58,7 @@
             "spanNulls": false,
             "stacking": {
               "group": "A",
-              "mode": "none"
+              "mode": "normal"
             },
             "thresholdsStyle": {
               "mode": "off"
@@ -79,32 +79,7 @@
             ]
           }
         },
-        "overrides": [
-          {
-            "__systemRef": "hideSeriesFrom",
-            "matcher": {
-              "id": "byNames",
-              "options": {
-                "mode": "exclude",
-                "names": [
-                  "api_server"
-                ],
-                "prefix": "All except:",
-                "readOnly": true
-              }
-            },
-            "properties": [
-              {
-                "id": "custom.hideFrom",
-                "value": {
-                  "legend": false,
-                  "tooltip": false,
-                  "viz": true
-                }
-              }
-            ]
-          }
-        ]
+        "overrides": []
       },
       "gridPos": {
         "h": 8,
@@ -112,7 +87,7 @@
         "x": 0,
         "y": 0
       },
-      "id": 3,
+      "id": 5,
       "options": {
         "legend": {
           "calcs": [],
@@ -133,34 +108,18 @@
           },
           "disableTextWrap": false,
           "editorMode": "code",
-          "expr": "avg(rate(envoy_cluster_internal_upstream_rq_completed{envoy_cluster_name=~\"api_server|openai\"}[1m])) by (envoy_cluster_name)",
-          "fullMetaSearch": false,
-          "includeNullMetadata": true,
-          "instant": false,
-          "legendFormat": "__auto",
-          "range": true,
-          "refId": "A",
-          "useBackend": false
-        },
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "PBFA97CFB590B2093"
-          },
-          "disableTextWrap": false,
-          "editorMode": "code",
-          "expr": "avg(rate(envoy_cluster_external_upstream_rq_completed{envoy_cluster_name=~\"api_server|openai\"}[1m])) by (envoy_cluster_name)",
+          "expr": "avg(rate(envoy_cluster_external_upstream_rq_time_sum{envoy_cluster_name=\"api_server\"}[1m]) / rate(envoy_cluster_external_upstream_rq_time_count[1m])) by (envoy_cluster_name)",
           "fullMetaSearch": false,
           "hide": false,
           "includeNullMetadata": true,
           "instant": false,
           "legendFormat": "__auto",
           "range": true,
-          "refId": "B",
+          "refId": "A",
           "useBackend": false
         }
       ],
-      "title": "Upstream request rate",
+      "title": "request latency - developer api server (ms)",
       "type": "timeseries"
     },
     {
@@ -230,7 +189,7 @@
         "x": 12,
         "y": 0
       },
-      "id": 1,
+      "id": 4,
       "options": {
         "legend": {
           "calcs": [],
@@ -251,7 +210,7 @@
           },
           "disableTextWrap": false,
           "editorMode": "code",
-          "expr": "avg(rate (envoy_cluster_external_upstream_rq_time_sum{envoy_cluster_name=~\"api_server|openai\"}[1m])/ rate(envoy_cluster_external_upstream_rq_time_count{envoy_cluster_name=~\"api_server|openai\"}[1m])) by (envoy_cluster_name)",
+          "expr": "avg(rate(envoy_cluster_external_upstream_rq_time_sum{envoy_cluster_name!=\"hallucination\", envoy_cluster_name!=\"zeroshot\", envoy_cluster_name!=\"embeddings\", envoy_cluster_name!=\"arch_fc\", envoy_cluster_name!=\"api_server\"}[1m]) / rate(envoy_cluster_external_upstream_rq_time_count[1m])) by (envoy_cluster_name)",
           "fullMetaSearch": false,
           "hide": false,
           "includeNullMetadata": true,
@@ -274,7 +233,40 @@
       "fieldConfig": {
         "defaults": {
           "color": {
-            "mode": "thresholds"
+            "mode": "palette-classic"
+          },
+          "custom": {
+            "axisBorderShow": false,
+            "axisCenteredZero": false,
+            "axisColorMode": "text",
+            "axisLabel": "",
+            "axisPlacement": "auto",
+            "barAlignment": 0,
+            "barWidthFactor": 0.6,
+            "drawStyle": "bars",
+            "fillOpacity": 54,
+            "gradientMode": "none",
+            "hideFrom": {
+              "legend": false,
+              "tooltip": false,
+              "viz": false
+            },
+            "insertNulls": false,
+            "lineInterpolation": "linear",
+            "lineWidth": 1,
+            "pointSize": 5,
+            "scaleDistribution": {
+              "type": "linear"
+            },
+            "showPoints": "auto",
+            "spanNulls": false,
+            "stacking": {
+              "group": "A",
+              "mode": "normal"
+            },
+            "thresholdsStyle": {
+              "mode": "off"
+            }
           },
           "mappings": [],
           "thresholds": {
@@ -299,25 +291,19 @@
         "x": 0,
         "y": 8
       },
-      "id": 4,
+      "id": 1,
       "options": {
-        "colorMode": "value",
-        "graphMode": "area",
-        "justifyMode": "auto",
-        "orientation": "auto",
-        "percentChangeColorMode": "standard",
-        "reduceOptions": {
-          "calcs": [
-            "lastNotNull"
-          ],
-          "fields": "",
-          "values": false
+        "legend": {
+          "calcs": [],
+          "displayMode": "list",
+          "placement": "bottom",
+          "showLegend": true
         },
-        "showPercentChange": false,
-        "textMode": "auto",
-        "wideLayout": true
+        "tooltip": {
+          "mode": "single",
+          "sort": "none"
+        }
       },
-      "pluginVersion": "11.2.0",
       "targets": [
         {
           "datasource": {
@@ -325,20 +311,20 @@
             "uid": "PBFA97CFB590B2093"
           },
           "disableTextWrap": false,
-          "editorMode": "builder",
-          "exemplar": false,
-          "expr": "envoy_cluster_upstream_rq_completed{envoy_cluster_name=~\"openai|api_server\"}",
+          "editorMode": "code",
+          "expr": "avg(rate(envoy_cluster_external_upstream_rq_time_sum{envoy_cluster_name!=\"openai\",envoy_cluster_name!=\"arch_llm_listener\",envoy_cluster_name!=\"api_server\"}[1m]) / rate(envoy_cluster_external_upstream_rq_time_count[1m])) by (envoy_cluster_name)",
           "fullMetaSearch": false,
+          "hide": false,
           "includeNullMetadata": true,
-          "instant": true,
-          "legendFormat": "{{envoy_cluster_name}}",
-          "range": false,
+          "instant": false,
+          "legendFormat": "__auto",
+          "range": true,
           "refId": "A",
           "useBackend": false
         }
       ],
-      "title": "# of Completd Requests",
-      "type": "stat"
+      "title": "request latency - internal arch services (ms)",
+      "type": "timeseries"
     },
     {
       "datasource": {
@@ -349,7 +335,40 @@
       "fieldConfig": {
         "defaults": {
           "color": {
-            "mode": "thresholds"
+            "mode": "palette-classic"
+          },
+          "custom": {
+            "axisBorderShow": false,
+            "axisCenteredZero": false,
+            "axisColorMode": "text",
+            "axisLabel": "",
+            "axisPlacement": "auto",
+            "barAlignment": 0,
+            "barWidthFactor": 0.6,
+            "drawStyle": "line",
+            "fillOpacity": 0,
+            "gradientMode": "none",
+            "hideFrom": {
+              "legend": false,
+              "tooltip": false,
+              "viz": false
+            },
+            "insertNulls": false,
+            "lineInterpolation": "linear",
+            "lineWidth": 1,
+            "pointSize": 5,
+            "scaleDistribution": {
+              "type": "linear"
+            },
+            "showPoints": "auto",
+            "spanNulls": false,
+            "stacking": {
+              "group": "A",
+              "mode": "none"
+            },
+            "thresholdsStyle": {
+              "mode": "off"
+            }
           },
           "mappings": [],
           "thresholds": {
@@ -371,28 +390,22 @@
       "gridPos": {
         "h": 8,
         "w": 12,
-        "x": 12,
-        "y": 8
+        "x": 0,
+        "y": 16
       },
-      "id": 5,
+      "id": 3,
       "options": {
-        "colorMode": "value",
-        "graphMode": "area",
-        "justifyMode": "auto",
-        "orientation": "auto",
-        "percentChangeColorMode": "standard",
-        "reduceOptions": {
-          "calcs": [
-            "lastNotNull"
-          ],
-          "fields": "",
-          "values": false
+        "legend": {
+          "calcs": [],
+          "displayMode": "list",
+          "placement": "bottom",
+          "showLegend": true
         },
-        "showPercentChange": false,
-        "textMode": "auto",
-        "wideLayout": true
+        "tooltip": {
+          "mode": "single",
+          "sort": "none"
+        }
       },
-      "pluginVersion": "11.2.0",
       "targets": [
         {
           "datasource": {
@@ -400,23 +413,38 @@
             "uid": "PBFA97CFB590B2093"
           },
           "disableTextWrap": false,
-          "editorMode": "builder",
-          "exemplar": false,
-          "expr": "envoy_cluster_upstream_rq_cancelled{envoy_cluster_name=~\"api_server|openai\"} + envoy_cluster_upstream_rq_pending_failure_eject{envoy_cluster_name=~\"api_server|openai\"} + envoy_cluster_upstream_rq_pending_overflow{envoy_cluster_name=~\"api_server|openai\"}",
+          "editorMode": "code",
+          "expr": "avg(rate(envoy_cluster_internal_upstream_rq_completed{envoy_cluster_name !=\"opentelemetry_collector\"}[1m])) by (envoy_cluster_name)",
           "fullMetaSearch": false,
           "includeNullMetadata": true,
-          "instant": true,
-          "legendFormat": "{{envoy_cluster_name}}",
-          "range": false,
+          "instant": false,
+          "legendFormat": "__auto",
+          "range": true,
           "refId": "A",
           "useBackend": false
+        },
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "PBFA97CFB590B2093"
+          },
+          "disableTextWrap": false,
+          "editorMode": "code",
+          "expr": "avg(rate(envoy_cluster_external_upstream_rq_completed{envoy_cluster_name !=\"opentelemetry_collector\"}[1m])) by (envoy_cluster_name)",
+          "fullMetaSearch": false,
+          "hide": false,
+          "includeNullMetadata": true,
+          "instant": false,
+          "legendFormat": "__auto",
+          "range": true,
+          "refId": "B",
+          "useBackend": false
         }
       ],
-      "title": "# of Failed or Cancelled Requests",
-      "type": "stat"
+      "title": "Request count (per sec)",
+      "type": "timeseries"
     }
   ],
-  "refresh": "",
   "schemaVersion": 39,
   "tags": [],
   "templating": {
@@ -428,8 +456,8 @@
   },
   "timepicker": {},
   "timezone": "browser",
-  "title": "Arch Gateway Dashboard",
+  "title": "Intelligent Gateway Overview",
   "uid": "adt6uhx5lk8aob",
-  "version": 1,
+  "version": 14,
   "weekStart": ""
 }