Add additional instructions for re-testing.

Author: tjholm

docs/guides/python/ai-podcast-part-1.mdx

@@ -456,10 +456,26 @@ Nitric.run()
 
 Once that's done we can give the project another test, just to make sure everything is still working as expected.
 
+If nitric isn't still running you can start it again with:
+
 ```bash
 nitric start
 ```
 
+First we'll make sure that our new model download code is working by running:
+
+```bash
+curl -X POST http://localhost:4001/download-audio-model
+```
+
+Then we can test the audio generation again with:
+
+```bash
+curl -X POST http://localhost:4001/audio/test -d "Okay this is cool, but let's wait and see what comes next"
+```
+
+You should get a similiar result to before. The main difference is that the model will be downloaded and cached in a nitric bucket before the audio generation starts.
+
 ## Defining our service docker images
 
 So that the AI workload can use GPUs in the cloud we'll need to make sure it ships with drivers and libraries to support that. We can do this by specifying a custom Dockerfile for our batch service under `docker/torch.dockerfile`.