diff --git a/python/samples/02-agents/observability/README.md b/python/samples/02-agents/observability/README.md
index f456f93dd7d..566f4ca9ed5 100644
--- a/python/samples/02-agents/observability/README.md
+++ b/python/samples/02-agents/observability/README.md
@@ -208,6 +208,40 @@ configure_otel_providers(exporters=[exporter])
 enable_sensitive_telemetry()
 ```
 
+Or with [Arize AX](https://arize.com/docs/ax/integrations/python-agent-frameworks/microsoft/microsoft-agent-framework) or [Phoenix](https://arize.com/docs/phoenix), using the [`openinference-instrumentation-agent-framework`](https://github.com/Arize-ai/openinference/tree/main/python/instrumentation/openinference-instrumentation-agent-framework) span processor to convert Agent Framework's GenAI spans to OpenInference. Install `openinference-instrumentation-agent-framework>=0.1.13` and `opentelemetry-exporter-otlp-proto-http`.
+
+The processor must run before the exporter, so set up the tracer provider yourself rather than calling `configure_otel_providers()`. The example sends to Arize AX; for Phoenix, use the commented-out exporter:
+
+```python
+from opentelemetry import trace
+from opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExporter
+from opentelemetry.sdk.resources import Resource
+from opentelemetry.sdk.trace import TracerProvider
+from opentelemetry.sdk.trace.export import BatchSpanProcessor
+from openinference.instrumentation.agent_framework import AgentFrameworkToOpenInferenceProcessor
+from agent_framework.observability import enable_sensitive_telemetry
+
+# Arize AX: authenticate with your space ID and API key
+exporter = OTLPSpanExporter(
+    endpoint="https://otlp.arize.com/v1/traces",
+    headers={"arize-space-id": "<space_id>", "arize-api-key": "<api_key>"},
+)
+
+# Phoenix: use this exporter instead. localhost:6006 is a local `phoenix serve`;
+# replace it with your Phoenix endpoint if Phoenix runs elsewhere
+# exporter = OTLPSpanExporter(endpoint="http://localhost:6006/v1/traces")
+
+tracer_provider = TracerProvider(resource=Resource.create({"openinference.project.name": "<project_name>"}))
+tracer_provider.add_span_processor(AgentFrameworkToOpenInferenceProcessor())
+tracer_provider.add_span_processor(BatchSpanProcessor(exporter))
+trace.set_tracer_provider(tracer_provider)
+
+# Capture prompts, responses, and tool arguments; without this, spans have no
+# messages or inputs and outputs. Only enable in development or test environments,
+# as it may expose user or system secrets in production.
+enable_sensitive_telemetry()
+```
+
 **4. Manual setup**
 
 For full control, set up providers and exporters yourself. See [advanced_manual_setup_console_output.py](./advanced_manual_setup_console_output.py) for a complete example that sends traces, logs, and metrics to the console. The `create_resource()` helper in `agent_framework.observability` can build a resource with the appropriate service name and version from environment variables (or sensible defaults), although the sample does not use it.
@@ -240,6 +274,7 @@ Exporters are **not** installed by default — install only what you need:
 - **Application Insights**: `azure-monitor-opentelemetry`
 - **Aspire Dashboard or other OTLP/gRPC backends**: `opentelemetry-exporter-otlp-proto-grpc`
 - **OTLP over HTTP**: `opentelemetry-exporter-otlp-proto-http`
+- **Arize AX or Phoenix**: `openinference-instrumentation-agent-framework>=0.1.13` and `opentelemetry-exporter-otlp-proto-http`
 
 For other backends, refer to the documentation of the specific exporter.