feat(analytics): Agentic usage

app/_how-tos/ai-gateway/proxy-a2a-agents.md

@@ -43,6 +43,8 @@ related_resources:
     url: https://a2a-protocol.org/latest/
   - text: Set up Jaeger with Gen AI OpenTelemetry
     url: /how-to/set-up-jaeger-with-gen-ai-otel/
+  - text: Agentic usage analytics in {{site.konnect_short_name}}
+    url: /observability/explorer/?tab=agentic-usage#metrics
 
 prereqs:
   entities:

app/_kong_plugins/ai-a2a-proxy/index.md

@@ -216,6 +216,8 @@ unlimited capture for request detection.
 {:.warning}
 > Payload logging may expose sensitive data. Enable with care in production environments.
 
+You can view AI A2A Proxy analytics in {{site.konnect_short_name}} Explorer and Dashboards using the [Agentic usage analytics](/observability/explorer/?tab=agentic-usage#metrics).
+
 ### Log output fields
 
 {% include /plugins/ai-a2a-proxy/log-output-fields.md %}

app/_landing_pages/ai-gateway/a2a.yaml

@@ -96,7 +96,7 @@ rows:
                     - Audit logs capture task IDs, JSON-RPC method calls, payloads, latencies, and errors.
                     - OpenTelemetry spans record task state, context IDs, TTFB, SSE event counts, and response sizes.
                     - Log plugins (File Log, HTTP Log, TCP Log, and others) consume the structured `ai.a2a` namespace emitted by the AI A2A Proxy plugin.
-  - column_count: 2
+  - column_count: 3
     columns:
       - blocks:
         - type: card
@@ -134,6 +134,15 @@ rows:
             cta:
               url: /ai-gateway/ai-otel-metrics/#a2a-metrics
               align: end
+      - blocks:
+        - type: card
+          config:
+            title: Agentic usage analytics in {{site.konnect_short_name}}
+            description: View A2A-specific metrics and analytics in {{site.konnect_short_name}}.
+            icon: /assets/icons/KogoBlue.svg
+            cta:
+              url: /observability/explorer/?tab=agentic-usage#metrics
+              align: end
 
   - header:
       type: h2

app/observability/explorer.md

@@ -268,6 +268,44 @@ rows:
 {% endtable %}
 <!--vale on-->
 {% endnavtab %}
+{% navtab "Agentic usage" %}
+
+Agentic usage tracks analytics data for agent-to-agent (A2A) traffic that flows through the [AI A2A Proxy plugin](/plugins/ai-a2a-proxy/).
+You must [configure the AI A2A Proxy plugin](/how-to/proxy-a2a-agents/) before analytics display in {{site.konnect_short_name}} Explorer.
+
+With agentic usage reporting, you can:
+* See how many times a tool was called
+* View the most called tools
+* See which tools are returning errors
+* View the latency for tools
+
+
+The following table shows the agentic usage-specific metrics you can view:
+<!--vale off-->
+{% table %}
+columns:
+  - title: "Metric"
+    key: "metric"
+  - title: "Category"
+    key: "category"
+  - title: "Description"
+    key: "description"
+rows:
+  - metric: "A2A latency"
+    category: "Latency"
+    description: |
+      The amount of time, in milliseconds, that {{site.base_gateway}} was waiting for the first byte of the agent's response. Users can select average (avg).
+  - metric: "MCP Response Size"
+    category: "Size"
+    description: |
+      The size of the response payload returned to {{site.base_gateway}} from the MCP server, in bytes. Users can select the total sum.
+  - metric: "A2A Response Size"
+    category: "Size"
+    description: |
+      The size of the response payload returned to {{site.base_gateway}} from an agent, in bytes. Users can select the total sum.
+{% endtable %}
+<!--vale on-->
+{% endnavtab %}
 {% endnavtabs %}
 
 ## Time intervals